id	sid	tid	token	lemma	pos
tedunderwood-com-8283	1	1	A	a	DT
tedunderwood-com-8283	1	2	half	half	JJ
tedunderwood-com-8283	1	3	-	-	HYPH
tedunderwood-com-8283	1	4	decent	decent	JJ
tedunderwood-com-8283	1	5	OCR	ocr	NN
tedunderwood-com-8283	1	6	normalizer	normalizer	NN
tedunderwood-com-8283	1	7	for	for	IN
tedunderwood-com-8283	1	8	English	English	NNP
tedunderwood-com-8283	1	9	texts	text	NNS
tedunderwood-com-8283	1	10	after	after	IN
tedunderwood-com-8283	1	11	1700	1700	CD
tedunderwood-com-8283	1	12	.	.	.
tedunderwood-com-8283	2	1	|	|	NNP
tedunderwood-com-8283	2	2	The	The	NNP
tedunderwood-com-8283	2	3	Stone	Stone	NNP
tedunderwood-com-8283	2	4	and	and	CC
tedunderwood-com-8283	2	5	the	the	DT
tedunderwood-com-8283	2	6	Shell	Shell	NNP
tedunderwood-com-8283	2	7	The	The	NNP
tedunderwood-com-8283	2	8	Stone	Stone	NNP
tedunderwood-com-8283	2	9	and	and	CC
tedunderwood-com-8283	2	10	the	the	DT
tedunderwood-com-8283	2	11	Shell	Shell	NNP
tedunderwood-com-8283	2	12	Using	use	VBG
tedunderwood-com-8283	2	13	large	large	JJ
tedunderwood-com-8283	2	14	digital	digital	JJ
tedunderwood-com-8283	2	15	libraries	library	NNS
tedunderwood-com-8283	2	16	to	to	TO
tedunderwood-com-8283	2	17	advance	advance	VB
tedunderwood-com-8283	2	18	literary	literary	JJ
tedunderwood-com-8283	2	19	history	history	NN
tedunderwood-com-8283	2	20	Search	Search	NNP
tedunderwood-com-8283	2	21	Main	Main	NNP
tedunderwood-com-8283	2	22	menu	menu	NN
tedunderwood-com-8283	2	23	Skip	Skip	NNP
tedunderwood-com-8283	2	24	to	to	IN
tedunderwood-com-8283	2	25	primary	primary	JJ
tedunderwood-com-8283	2	26	content	content	NN
tedunderwood-com-8283	2	27	Home	home	NN
tedunderwood-com-8283	2	28	18c	18c	CD
tedunderwood-com-8283	2	29	tree	tree	NN
tedunderwood-com-8283	2	30	About	about	IN
tedunderwood-com-8283	2	31	this	this	DT
tedunderwood-com-8283	2	32	blog	blog	NN
tedunderwood-com-8283	2	33	Open	open	JJ
tedunderwood-com-8283	2	34	data	datum	NNS
tedunderwood-com-8283	2	35	Tech	Tech	NNP
tedunderwood-com-8283	2	36	note	note	NN
tedunderwood-com-8283	2	37	Ted	Ted	NNP
tedunderwood-com-8283	2	38	Underwood	Underwood	NNP
tedunderwood-com-8283	2	39	Post	Post	NNP
tedunderwood-com-8283	2	40	navigation	navigation	NN
tedunderwood-com-8283	2	41	←	←	VBZ
tedunderwood-com-8283	2	42	Previous	previous	JJ
tedunderwood-com-8283	2	43	Next	Next	NNP
tedunderwood-com-8283	2	44	→	→	SYM
tedunderwood-com-8283	2	45	A	a	DT
tedunderwood-com-8283	2	46	half	half	JJ
tedunderwood-com-8283	2	47	-	-	HYPH
tedunderwood-com-8283	2	48	decent	decent	JJ
tedunderwood-com-8283	2	49	OCR	ocr	NN
tedunderwood-com-8283	2	50	normalizer	normalizer	NN
tedunderwood-com-8283	2	51	for	for	IN
tedunderwood-com-8283	2	52	English	English	NNP
tedunderwood-com-8283	2	53	texts	text	NNS
tedunderwood-com-8283	2	54	after	after	IN
tedunderwood-com-8283	2	55	 	  	_SP
tedunderwood-com-8283	2	56	1700	1700	CD
tedunderwood-com-8283	2	57	.	.	.
tedunderwood-com-8283	3	1	Posted	post	VBN
tedunderwood-com-8283	3	2	on	on	IN
tedunderwood-com-8283	3	3	December	December	NNP
tedunderwood-com-8283	3	4	10	10	CD
tedunderwood-com-8283	3	5	,	,	,
tedunderwood-com-8283	3	6	2013	2013	CD
tedunderwood-com-8283	3	7	by	by	IN
tedunderwood-com-8283	3	8	tedunderwood	tedunderwood	NN
tedunderwood-com-8283	3	9	Perhaps	perhaps	RB
tedunderwood-com-8283	3	10	not	not	RB
tedunderwood-com-8283	3	11	the	the	DT
tedunderwood-com-8283	3	12	most	most	RBS
tedunderwood-com-8283	3	13	inspiring	inspiring	JJ
tedunderwood-com-8283	3	14	title	title	NN
tedunderwood-com-8283	3	15	.	.	.
tedunderwood-com-8283	4	1	But	but	CC
tedunderwood-com-8283	4	2	the	the	DT
tedunderwood-com-8283	4	3	words	word	NNS
tedunderwood-com-8283	4	4	are	be	VBP
tedunderwood-com-8283	4	5	carefully	carefully	RB
tedunderwood-com-8283	4	6	chosen	choose	VBN
tedunderwood-com-8283	4	7	.	.	.
tedunderwood-com-8283	5	1	Basically	basically	RB
tedunderwood-com-8283	5	2	,	,	,
tedunderwood-com-8283	5	3	I	-PRON-	PRP
tedunderwood-com-8283	5	4	’m	be	VBP
tedunderwood-com-8283	5	5	sharing	share	VBG
tedunderwood-com-8283	5	6	the	the	DT
tedunderwood-com-8283	5	7	code	code	NN
tedunderwood-com-8283	5	8	I	-PRON-	PRP
tedunderwood-com-8283	5	9	use	use	VBP
tedunderwood-com-8283	5	10	to	to	TO
tedunderwood-com-8283	5	11	correct	correct	VB
tedunderwood-com-8283	5	12	OCR	ocr	NN
tedunderwood-com-8283	5	13	in	in	IN
tedunderwood-com-8283	5	14	my	-PRON-	PRP$
tedunderwood-com-8283	5	15	own	own	JJ
tedunderwood-com-8283	5	16	research	research	NN
tedunderwood-com-8283	5	17	.	.	.
tedunderwood-com-8283	6	1	I	-PRON-	PRP
tedunderwood-com-8283	6	2	’ve	have	VB
tedunderwood-com-8283	6	3	shared	share	VBN
tedunderwood-com-8283	6	4	parts	part	NNS
tedunderwood-com-8283	6	5	of	of	IN
tedunderwood-com-8283	6	6	this	this	DT
tedunderwood-com-8283	6	7	before	before	RB
tedunderwood-com-8283	6	8	,	,	,
tedunderwood-com-8283	6	9	but	but	CC
tedunderwood-com-8283	6	10	this	this	DT
tedunderwood-com-8283	6	11	is	be	VBZ
tedunderwood-com-8283	6	12	the	the	DT
tedunderwood-com-8283	6	13	first	first	JJ
tedunderwood-com-8283	6	14	time	time	NN
tedunderwood-com-8283	6	15	I	-PRON-	PRP
tedunderwood-com-8283	6	16	’ve	have	VB
tedunderwood-com-8283	6	17	made	make	VBN
tedunderwood-com-8283	6	18	any	any	DT
tedunderwood-com-8283	6	19	effort	effort	NN
tedunderwood-com-8283	6	20	to	to	TO
tedunderwood-com-8283	6	21	package	package	VB
tedunderwood-com-8283	6	22	it	-PRON-	PRP
tedunderwood-com-8283	6	23	so	so	IN
tedunderwood-com-8283	6	24	that	that	IN
tedunderwood-com-8283	6	25	it	-PRON-	PRP
tedunderwood-com-8283	6	26	will	will	MD
tedunderwood-com-8283	6	27	run	run	VB
tedunderwood-com-8283	6	28	on	on	IN
tedunderwood-com-8283	6	29	other	other	JJ
tedunderwood-com-8283	6	30	people	people	NNS
tedunderwood-com-8283	6	31	’s	’s	POS
tedunderwood-com-8283	6	32	machines	machine	NNS
tedunderwood-com-8283	6	33	.	.	.
tedunderwood-com-8283	7	1	If	if	IN
tedunderwood-com-8283	7	2	you	-PRON-	PRP
tedunderwood-com-8283	7	3	’ve	have	VB
tedunderwood-com-8283	7	4	got	get	VBD
tedunderwood-com-8283	7	5	Python	Python	NNP
tedunderwood-com-8283	7	6	3.x	3.x	CD
tedunderwood-com-8283	7	7	,	,	,
tedunderwood-com-8283	7	8	you	-PRON-	PRP
tedunderwood-com-8283	7	9	should	should	MD
tedunderwood-com-8283	7	10	be	be	VB
tedunderwood-com-8283	7	11	able	able	JJ
tedunderwood-com-8283	7	12	to	to	TO
tedunderwood-com-8283	7	13	clone	clone	VB
tedunderwood-com-8283	7	14	this	this	DT
tedunderwood-com-8283	7	15	github	github	NNP
tedunderwood-com-8283	7	16	repository	repository	NN
tedunderwood-com-8283	7	17	,	,	,
tedunderwood-com-8283	7	18	run	run	VBP
tedunderwood-com-8283	7	19	OCRnormalizer.py	OCRnormalizer.py	NNS
tedunderwood-com-8283	7	20	,	,	,
tedunderwood-com-8283	7	21	and	and	CC
tedunderwood-com-8283	7	22	point	point	VB
tedunderwood-com-8283	7	23	it	-PRON-	PRP
tedunderwood-com-8283	7	24	at	at	IN
tedunderwood-com-8283	7	25	a	a	DT
tedunderwood-com-8283	7	26	folder	folder	NN
tedunderwood-com-8283	7	27	of	of	IN
tedunderwood-com-8283	7	28	files	file	NNS
tedunderwood-com-8283	7	29	you	-PRON-	PRP
tedunderwood-com-8283	7	30	want	want	VBP
tedunderwood-com-8283	7	31	corrected	correct	VBN
tedunderwood-com-8283	7	32	.	.	.
tedunderwood-com-8283	8	1	The	the	DT
tedunderwood-com-8283	8	2	script	script	NN
tedunderwood-com-8283	8	3	is	be	VBZ
tedunderwood-com-8283	8	4	designed	design	VBN
tedunderwood-com-8283	8	5	to	to	TO
tedunderwood-com-8283	8	6	handle	handle	VB
tedunderwood-com-8283	8	7	data	data	NN
tedunderwood-com-8283	8	8	structures	structure	NNS
tedunderwood-com-8283	8	9	from	from	IN
tedunderwood-com-8283	8	10	HathiTrust	HathiTrust	NNP
tedunderwood-com-8283	8	11	,	,	,
tedunderwood-com-8283	8	12	so	so	RB
tedunderwood-com-8283	8	13	(	(	-LRB-
tedunderwood-com-8283	8	14	for	for	IN
tedunderwood-com-8283	8	15	instance	instance	NN
tedunderwood-com-8283	8	16	)	)	-RRB-
tedunderwood-com-8283	8	17	if	if	IN
tedunderwood-com-8283	8	18	you	-PRON-	PRP
tedunderwood-com-8283	8	19	have	have	VBP
tedunderwood-com-8283	8	20	zip	zip	NN
tedunderwood-com-8283	8	21	files	file	NNS
tedunderwood-com-8283	8	22	contained	contain	VBN
tedunderwood-com-8283	8	23	in	in	IN
tedunderwood-com-8283	8	24	a	a	DT
tedunderwood-com-8283	8	25	pairtree	pairtree	NN
tedunderwood-com-8283	8	26	structure	structure	NN
tedunderwood-com-8283	8	27	,	,	,
tedunderwood-com-8283	8	28	it	-PRON-	PRP
tedunderwood-com-8283	8	29	will	will	MD
tedunderwood-com-8283	8	30	recursively	recursively	RB
tedunderwood-com-8283	8	31	walk	walk	VB
tedunderwood-com-8283	8	32	the	the	DT
tedunderwood-com-8283	8	33	directories	directory	NNS
tedunderwood-com-8283	8	34	to	to	TO
tedunderwood-com-8283	8	35	identify	identify	VB
tedunderwood-com-8283	8	36	all	all	DT
tedunderwood-com-8283	8	37	zip	zip	NN
tedunderwood-com-8283	8	38	files	file	NNS
tedunderwood-com-8283	8	39	,	,	,
tedunderwood-com-8283	8	40	concatenate	concatenate	NN
tedunderwood-com-8283	8	41	pages	page	NNS
tedunderwood-com-8283	8	42	,	,	,
tedunderwood-com-8283	8	43	and	and	CC
tedunderwood-com-8283	8	44	write	write	VB
tedunderwood-com-8283	8	45	a	a	DT
tedunderwood-com-8283	8	46	file	file	NN
tedunderwood-com-8283	8	47	with	with	IN
tedunderwood-com-8283	8	48	the	the	DT
tedunderwood-com-8283	8	49	suffix	suffix	NN
tedunderwood-com-8283	8	50	“	"	``
tedunderwood-com-8283	8	51	.clean.txt	.clean.txt	.
tedunderwood-com-8283	8	52	”	"	''
tedunderwood-com-8283	8	53	in	in	IN
tedunderwood-com-8283	8	54	the	the	DT
tedunderwood-com-8283	8	55	same	same	JJ
tedunderwood-com-8283	8	56	folder	folder	NN
tedunderwood-com-8283	8	57	where	where	WRB
tedunderwood-com-8283	8	58	each	each	DT
tedunderwood-com-8283	8	59	zip	zip	NN
tedunderwood-com-8283	8	60	file	file	NN
tedunderwood-com-8283	8	61	lives	live	VBZ
tedunderwood-com-8283	8	62	.	.	.
tedunderwood-com-8283	9	1	But	but	CC
tedunderwood-com-8283	9	2	it	-PRON-	PRP
tedunderwood-com-8283	9	3	can	can	MD
tedunderwood-com-8283	9	4	also	also	RB
tedunderwood-com-8283	9	5	work	work	VB
tedunderwood-com-8283	9	6	on	on	IN
tedunderwood-com-8283	9	7	files	file	NNS
tedunderwood-com-8283	9	8	from	from	IN
tedunderwood-com-8283	9	9	another	another	DT
tedunderwood-com-8283	9	10	source	source	NN
tedunderwood-com-8283	9	11	.	.	.
tedunderwood-com-8283	10	1	If	if	IN
tedunderwood-com-8283	10	2	you	-PRON-	PRP
tedunderwood-com-8283	10	3	point	point	VBP
tedunderwood-com-8283	10	4	it	-PRON-	PRP
tedunderwood-com-8283	10	5	at	at	IN
tedunderwood-com-8283	10	6	a	a	DT
tedunderwood-com-8283	10	7	flat	flat	JJ
tedunderwood-com-8283	10	8	folder	folder	NN
tedunderwood-com-8283	10	9	of	of	IN
tedunderwood-com-8283	10	10	generic	generic	JJ
tedunderwood-com-8283	10	11	text	text	NN
tedunderwood-com-8283	10	12	files	file	NNS
tedunderwood-com-8283	10	13	,	,	,
tedunderwood-com-8283	10	14	it	-PRON-	PRP
tedunderwood-com-8283	10	15	will	will	MD
tedunderwood-com-8283	10	16	correct	correct	VB
tedunderwood-com-8283	10	17	those	those	DT
tedunderwood-com-8283	10	18	.	.	.
tedunderwood-com-8283	11	1	I	-PRON-	PRP
tedunderwood-com-8283	11	2	’m	be	VBP
tedunderwood-com-8283	11	3	calling	call	VBG
tedunderwood-com-8283	11	4	this	this	DT
tedunderwood-com-8283	11	5	an	an	DT
tedunderwood-com-8283	11	6	OCR	OCR	NNP
tedunderwood-com-8283	11	7	“	"	``
tedunderwood-com-8283	11	8	normalizer	normalizer	NN
tedunderwood-com-8283	11	9	”	"	''
tedunderwood-com-8283	11	10	rather	rather	RB
tedunderwood-com-8283	11	11	than	than	IN
tedunderwood-com-8283	11	12	“	"	``
tedunderwood-com-8283	11	13	corrector	corrector	NN
tedunderwood-com-8283	11	14	”	"	''
tedunderwood-com-8283	11	15	because	because	IN
tedunderwood-com-8283	11	16	it	-PRON-	PRP
tedunderwood-com-8283	11	17	’s	’	VBZ
tedunderwood-com-8283	11	18	designed	design	VBN
tedunderwood-com-8283	11	19	to	to	TO
tedunderwood-com-8283	11	20	accomplish	accomplish	VB
tedunderwood-com-8283	11	21	very	very	RB
tedunderwood-com-8283	11	22	specific	specific	JJ
tedunderwood-com-8283	11	23	goals	goal	NNS
tedunderwood-com-8283	11	24	.	.	.
tedunderwood-com-8283	12	1	In	in	IN
tedunderwood-com-8283	12	2	my	-PRON-	PRP$
tedunderwood-com-8283	12	3	research	research	NN
tedunderwood-com-8283	12	4	,	,	,
tedunderwood-com-8283	12	5	I	-PRON-	PRP
tedunderwood-com-8283	12	6	’m	be	VBP
tedunderwood-com-8283	12	7	mainly	mainly	RB
tedunderwood-com-8283	12	8	concerned	concern	VBN
tedunderwood-com-8283	12	9	with	with	IN
tedunderwood-com-8283	12	10	the	the	DT
tedunderwood-com-8283	12	11	kinds	kind	NNS
tedunderwood-com-8283	12	12	of	of	IN
tedunderwood-com-8283	12	13	errors	error	NNS
tedunderwood-com-8283	12	14	that	that	WDT
tedunderwood-com-8283	12	15	become	become	VBP
tedunderwood-com-8283	12	16	problems	problem	NNS
tedunderwood-com-8283	12	17	for	for	IN
tedunderwood-com-8283	12	18	diachronic	diachronic	JJ
tedunderwood-com-8283	12	19	text	text	NN
tedunderwood-com-8283	12	20	mining	mining	NN
tedunderwood-com-8283	12	21	.	.	.
tedunderwood-com-8283	13	1	The	the	DT
tedunderwood-com-8283	13	2	algorithms	algorithm	NNS
tedunderwood-com-8283	13	3	I	-PRON-	PRP
tedunderwood-com-8283	13	4	use	use	VBP
tedunderwood-com-8283	13	5	can	can	MD
tedunderwood-com-8283	13	6	handle	handle	VB
tedunderwood-com-8283	13	7	a	a	DT
tedunderwood-com-8283	13	8	pretty	pretty	RB
tedunderwood-com-8283	13	9	high	high	JJ
tedunderwood-com-8283	13	10	level	level	NN
tedunderwood-com-8283	13	11	of	of	IN
tedunderwood-com-8283	13	12	error	error	NN
tedunderwood-com-8283	13	13	as	as	RB
tedunderwood-com-8283	13	14	long	long	RB
tedunderwood-com-8283	13	15	as	as	IN
tedunderwood-com-8283	13	16	those	those	DT
tedunderwood-com-8283	13	17	errors	error	NNS
tedunderwood-com-8283	13	18	are	be	VBP
tedunderwood-com-8283	13	19	distributed	distribute	VBN
tedunderwood-com-8283	13	20	in	in	IN
tedunderwood-com-8283	13	21	a	a	DT
tedunderwood-com-8283	13	22	more	more	RBR
tedunderwood-com-8283	13	23	-	-	HYPH
tedunderwood-com-8283	13	24	or	or	CC
tedunderwood-com-8283	13	25	-	-	HYPH
tedunderwood-com-8283	13	26	less	less	RBR
tedunderwood-com-8283	13	27	random	random	JJ
tedunderwood-com-8283	13	28	way	way	NN
tedunderwood-com-8283	13	29	.	.	.
tedunderwood-com-8283	14	1	If	if	IN
tedunderwood-com-8283	14	2	a	a	DT
tedunderwood-com-8283	14	3	word	word	NN
tedunderwood-com-8283	14	4	is	be	VBZ
tedunderwood-com-8283	14	5	mistranscribed	mistranscribe	VBN
tedunderwood-com-8283	14	6	randomly	randomly	RB
tedunderwood-com-8283	14	7	in	in	IN
tedunderwood-com-8283	14	8	200	200	CD
tedunderwood-com-8283	14	9	different	different	JJ
tedunderwood-com-8283	14	10	ways	way	NNS
tedunderwood-com-8283	14	11	,	,	,
tedunderwood-com-8283	14	12	each	each	DT
tedunderwood-com-8283	14	13	of	of	IN
tedunderwood-com-8283	14	14	those	those	DT
tedunderwood-com-8283	14	15	errors	error	NNS
tedunderwood-com-8283	14	16	may	may	MD
tedunderwood-com-8283	14	17	be	be	VB
tedunderwood-com-8283	14	18	rare	rare	JJ
tedunderwood-com-8283	14	19	enough	enough	RB
tedunderwood-com-8283	14	20	to	to	TO
tedunderwood-com-8283	14	21	drop	drop	VB
tedunderwood-com-8283	14	22	out	out	IN
tedunderwood-com-8283	14	23	of	of	IN
tedunderwood-com-8283	14	24	the	the	DT
tedunderwood-com-8283	14	25	analysis	analysis	NN
tedunderwood-com-8283	14	26	.	.	.
tedunderwood-com-8283	15	1	You	-PRON-	PRP
tedunderwood-com-8283	15	2	do	do	VBP
tedunderwood-com-8283	15	3	n’t	not	RB
tedunderwood-com-8283	15	4	necessarily	necessarily	RB
tedunderwood-com-8283	15	5	have	have	VB
tedunderwood-com-8283	15	6	to	to	TO
tedunderwood-com-8283	15	7	catch	catch	VB
tedunderwood-com-8283	15	8	them	-PRON-	PRP
tedunderwood-com-8283	15	9	all	all	DT
tedunderwood-com-8283	15	10	.	.	.
tedunderwood-com-8283	16	1	The	the	DT
tedunderwood-com-8283	16	2	percentage	percentage	NN
tedunderwood-com-8283	16	3	of	of	IN
tedunderwood-com-8283	16	4	tokens	token	NNS
tedunderwood-com-8283	16	5	in	in	IN
tedunderwood-com-8283	16	6	the	the	DT
tedunderwood-com-8283	16	7	HathiTrust	HathiTrust	NNP
tedunderwood-com-8283	16	8	corpus	corpus	NN
tedunderwood-com-8283	16	9	that	that	WDT
tedunderwood-com-8283	16	10	are	be	VBP
tedunderwood-com-8283	16	11	recognized	recognize	VBN
tedunderwood-com-8283	16	12	as	as	IN
tedunderwood-com-8283	16	13	words	word	NNS
tedunderwood-com-8283	16	14	before	before	IN
tedunderwood-com-8283	16	15	(	(	-LRB-
tedunderwood-com-8283	16	16	red	red	NNP
tedunderwood-com-8283	16	17	)	)	-RRB-
tedunderwood-com-8283	16	18	and	and	CC
tedunderwood-com-8283	16	19	after	after	IN
tedunderwood-com-8283	16	20	(	(	-LRB-
tedunderwood-com-8283	16	21	black	black	JJ
tedunderwood-com-8283	16	22	)	)	-RRB-
tedunderwood-com-8283	16	23	correction	correction	NN
tedunderwood-com-8283	16	24	by	by	IN
tedunderwood-com-8283	16	25	my	-PRON-	PRP$
tedunderwood-com-8283	16	26	script	script	NN
tedunderwood-com-8283	16	27	.	.	.
tedunderwood-com-8283	17	1	Technically	technically	RB
tedunderwood-com-8283	17	2	this	this	DT
tedunderwood-com-8283	17	3	is	be	VBZ
tedunderwood-com-8283	17	4	not	not	RB
tedunderwood-com-8283	17	5	“	"	``
tedunderwood-com-8283	17	6	recall	recall	VB
tedunderwood-com-8283	17	7	”	"	''
tedunderwood-com-8283	17	8	but	but	CC
tedunderwood-com-8283	17	9	a	a	DT
tedunderwood-com-8283	17	10	count	count	NN
tedunderwood-com-8283	17	11	of	of	IN
tedunderwood-com-8283	17	12	(	(	-LRB-
tedunderwood-com-8283	17	13	true	true	JJ
tedunderwood-com-8283	17	14	and	and	CC
tedunderwood-com-8283	17	15	false	false	JJ
tedunderwood-com-8283	17	16	)	)	-RRB-
tedunderwood-com-8283	17	17	“	"	``
tedunderwood-com-8283	17	18	positives	positive	NNS
tedunderwood-com-8283	17	19	.	.	.
tedunderwood-com-8283	17	20	”	"	''
tedunderwood-com-8283	17	21	The	the	DT
tedunderwood-com-8283	17	22	errors	error	NNS
tedunderwood-com-8283	17	23	that	that	WDT
tedunderwood-com-8283	17	24	become	become	VBP
tedunderwood-com-8283	17	25	problems	problem	NNS
tedunderwood-com-8283	17	26	are	be	VBP
tedunderwood-com-8283	17	27	the	the	DT
tedunderwood-com-8283	17	28	ones	one	NNS
tedunderwood-com-8283	17	29	that	that	WDT
tedunderwood-com-8283	17	30	cluster	cluster	VBP
tedunderwood-com-8283	17	31	in	in	IN
tedunderwood-com-8283	17	32	particular	particular	JJ
tedunderwood-com-8283	17	33	words	word	NNS
tedunderwood-com-8283	17	34	or	or	CC
tedunderwood-com-8283	17	35	periods	period	NNS
tedunderwood-com-8283	17	36	.	.	.
tedunderwood-com-8283	18	1	The	the	DT
tedunderwood-com-8283	18	2	notorious	notorious	JJ
tedunderwood-com-8283	18	3	example	example	NN
tedunderwood-com-8283	18	4	is	be	VBZ
tedunderwood-com-8283	18	5	eighteenth	eighteenth	JJ
tedunderwood-com-8283	18	6	-	-	HYPH
tedunderwood-com-8283	18	7	century	century	NN
tedunderwood-com-8283	18	8	“	"	``
tedunderwood-com-8283	18	9	long	long	JJ
tedunderwood-com-8283	18	10	S	S	NNP
tedunderwood-com-8283	18	11	,	,	,
tedunderwood-com-8283	18	12	”	"	''
tedunderwood-com-8283	18	13	which	which	WDT
tedunderwood-com-8283	18	14	caufes	caufe	VBZ
tedunderwood-com-8283	18	15	subftantial	subftantial	JJ
tedunderwood-com-8283	18	16	diflortions	diflortion	NNS
tedunderwood-com-8283	18	17	before	before	IN
tedunderwood-com-8283	18	18	1820	1820	CD
tedunderwood-com-8283	18	19	.	.	.
tedunderwood-com-8283	19	1	Other	other	JJ
tedunderwood-com-8283	19	2	errors	error	NNS
tedunderwood-com-8283	19	3	caused	cause	VBN
tedunderwood-com-8283	19	4	by	by	IN
tedunderwood-com-8283	19	5	ligaturcs	ligaturcs	NNP
tedunderwood-com-8283	19	6	and	and	CC
tedunderwood-com-8283	19	7	worn	wear	VBN
tedunderwood-com-8283	19	8	typc	typc	NN
tedunderwood-com-8283	19	9	also	also	RB
tedunderwood-com-8283	19	10	tend	tend	VBP
tedunderwood-com-8283	19	11	to	to	TO
tedunderwood-com-8283	19	12	cluster	cluster	VB
tedunderwood-com-8283	19	13	toward	toward	IN
tedunderwood-com-8283	19	14	the	the	DT
tedunderwood-com-8283	19	15	early	early	JJ
tedunderwood-com-8283	19	16	end	end	NN
tedunderwood-com-8283	19	17	of	of	IN
tedunderwood-com-8283	19	18	the	the	DT
tedunderwood-com-8283	19	19	timeline	timeline	NN
tedunderwood-com-8283	19	20	.	.	.
tedunderwood-com-8283	20	1	But	but	CC
tedunderwood-com-8283	20	2	as	as	IN
tedunderwood-com-8283	20	3	you	-PRON-	PRP
tedunderwood-com-8283	20	4	can	can	MD
tedunderwood-com-8283	20	5	see	see	VB
tedunderwood-com-8283	20	6	in	in	IN
tedunderwood-com-8283	20	7	the	the	DT
tedunderwood-com-8283	20	8	illustration	illustration	NN
tedunderwood-com-8283	20	9	above	above	RB
tedunderwood-com-8283	20	10	,	,	,
tedunderwood-com-8283	20	11	long	long	JJ
tedunderwood-com-8283	20	12	S	S	NNP
tedunderwood-com-8283	20	13	is	be	VBZ
tedunderwood-com-8283	20	14	a	a	DT
tedunderwood-com-8283	20	15	particularly	particularly	RB
tedunderwood-com-8283	20	16	big	big	JJ
tedunderwood-com-8283	20	17	issue	issue	NN
tedunderwood-com-8283	20	18	;	;	:
tedunderwood-com-8283	20	19	there	there	EX
tedunderwood-com-8283	20	20	’s	’	VBZ
tedunderwood-com-8283	20	21	a	a	DT
tedunderwood-com-8283	20	22	major	major	JJ
tedunderwood-com-8283	20	23	improvement	improvement	NN
tedunderwood-com-8283	20	24	in	in	IN
tedunderwood-com-8283	20	25	OCR	ocr	NN
tedunderwood-com-8283	20	26	transcription	transcription	NN
tedunderwood-com-8283	20	27	shortly	shortly	RB
tedunderwood-com-8283	20	28	after	after	IN
tedunderwood-com-8283	20	29	1800	1800	CD
tedunderwood-com-8283	20	30	as	as	IN
tedunderwood-com-8283	20	31	it	-PRON-	PRP
tedunderwood-com-8283	20	32	gets	get	VBZ
tedunderwood-com-8283	20	33	phased	phase	VBN
tedunderwood-com-8283	20	34	out	out	RP
tedunderwood-com-8283	20	35	.	.	.
tedunderwood-com-8283	21	1	The	the	DT
tedunderwood-com-8283	21	2	range	range	NN
tedunderwood-com-8283	21	3	of	of	IN
tedunderwood-com-8283	21	4	possible	possible	JJ
tedunderwood-com-8283	21	5	OCR	ocr	NN
tedunderwood-com-8283	21	6	errors	error	NNS
tedunderwood-com-8283	21	7	is	be	VBZ
tedunderwood-com-8283	21	8	close	close	JJ
tedunderwood-com-8283	21	9	to	to	TO
tedunderwood-com-8283	21	10	infinite	infinite	VB
tedunderwood-com-8283	21	11	.	.	.
tedunderwood-com-8283	22	1	It	-PRON-	PRP
tedunderwood-com-8283	22	2	would	would	MD
tedunderwood-com-8283	22	3	be	be	VB
tedunderwood-com-8283	22	4	impossible	impossible	JJ
tedunderwood-com-8283	22	5	to	to	TO
tedunderwood-com-8283	22	6	catch	catch	VB
tedunderwood-com-8283	22	7	them	-PRON-	PRP
tedunderwood-com-8283	22	8	all	all	DT
tedunderwood-com-8283	22	9	,	,	,
tedunderwood-com-8283	22	10	and	and	CC
tedunderwood-com-8283	22	11	as	as	IN
tedunderwood-com-8283	22	12	you	-PRON-	PRP
tedunderwood-com-8283	22	13	can	can	MD
tedunderwood-com-8283	22	14	see	see	VB
tedunderwood-com-8283	22	15	above	above	RB
tedunderwood-com-8283	22	16	,	,	,
tedunderwood-com-8283	22	17	my	-PRON-	PRP$
tedunderwood-com-8283	22	18	script	script	NN
tedunderwood-com-8283	22	19	does	do	VBZ
tedunderwood-com-8283	22	20	n’t	not	RB
tedunderwood-com-8283	22	21	.	.	.
tedunderwood-com-8283	23	1	For	for	IN
tedunderwood-com-8283	23	2	a	a	DT
tedunderwood-com-8283	23	3	lot	lot	NN
tedunderwood-com-8283	23	4	of	of	IN
tedunderwood-com-8283	23	5	nineteenth	nineteenth	JJ
tedunderwood-com-8283	23	6	-	-	HYPH
tedunderwood-com-8283	23	7	century	century	NN
tedunderwood-com-8283	23	8	texts	text	NNS
tedunderwood-com-8283	23	9	it	-PRON-	PRP
tedunderwood-com-8283	23	10	produces	produce	VBZ
tedunderwood-com-8283	23	11	a	a	DT
tedunderwood-com-8283	23	12	pretty	pretty	RB
tedunderwood-com-8283	23	13	small	small	JJ
tedunderwood-com-8283	23	14	improvement	improvement	NN
tedunderwood-com-8283	23	15	.	.	.
tedunderwood-com-8283	24	1	But	but	CC
tedunderwood-com-8283	24	2	it	-PRON-	PRP
tedunderwood-com-8283	24	3	does	do	VBZ
tedunderwood-com-8283	24	4	normalize	normalize	VB
tedunderwood-com-8283	24	5	major	major	JJ
tedunderwood-com-8283	24	6	variations	variation	NNS
tedunderwood-com-8283	24	7	(	(	-LRB-
tedunderwood-com-8283	24	8	like	like	UH
tedunderwood-com-8283	24	9	long	long	JJ
tedunderwood-com-8283	24	10	S	s	NN
tedunderwood-com-8283	24	11	)	)	-RRB-
tedunderwood-com-8283	24	12	that	that	WDT
tedunderwood-com-8283	24	13	would	would	MD
tedunderwood-com-8283	24	14	otherwise	otherwise	RB
tedunderwood-com-8283	24	15	create	create	VB
tedunderwood-com-8283	24	16	significant	significant	JJ
tedunderwood-com-8283	24	17	distortions	distortion	NNS
tedunderwood-com-8283	24	18	.	.	.
tedunderwood-com-8283	25	1	(	(	-LRB-
tedunderwood-com-8283	25	2	In	in	IN
tedunderwood-com-8283	25	3	cases	case	NNS
tedunderwood-com-8283	25	4	like	like	IN
tedunderwood-com-8283	25	5	fame	fame	NN
tedunderwood-com-8283	25	6	/	/	SYM
tedunderwood-com-8283	25	7	same	same	JJ
tedunderwood-com-8283	25	8	where	where	WRB
tedunderwood-com-8283	25	9	a	a	DT
tedunderwood-com-8283	25	10	word	word	NN
tedunderwood-com-8283	25	11	could	could	MD
tedunderwood-com-8283	25	12	be	be	VB
tedunderwood-com-8283	25	13	either	either	CC
tedunderwood-com-8283	25	14	an	an	DT
tedunderwood-com-8283	25	15	OCR	ocr	NN
tedunderwood-com-8283	25	16	error	error	NN
tedunderwood-com-8283	25	17	or	or	CC
tedunderwood-com-8283	25	18	a	a	DT
tedunderwood-com-8283	25	19	real	real	JJ
tedunderwood-com-8283	25	20	word	word	NN
tedunderwood-com-8283	25	21	,	,	,
tedunderwood-com-8283	25	22	it	-PRON-	PRP
tedunderwood-com-8283	25	23	uses	use	VBZ
tedunderwood-com-8283	25	24	the	the	DT
tedunderwood-com-8283	25	25	words	word	NNS
tedunderwood-com-8283	25	26	on	on	IN
tedunderwood-com-8283	25	27	either	either	DT
tedunderwood-com-8283	25	28	side	side	NN
tedunderwood-com-8283	25	29	to	to	TO
tedunderwood-com-8283	25	30	disambiguate	disambiguate	VB
tedunderwood-com-8283	25	31	.	.	.
tedunderwood-com-8283	25	32	)	)	-RRB-
tedunderwood-com-8283	26	1	Moreover	moreover	RB
tedunderwood-com-8283	26	2	,	,	,
tedunderwood-com-8283	26	3	certain	certain	JJ
tedunderwood-com-8283	26	4	things	thing	NNS
tedunderwood-com-8283	26	5	that	that	WDT
tedunderwood-com-8283	26	6	are	be	VBP
tedunderwood-com-8283	26	7	n’t	not	RB
tedunderwood-com-8283	26	8	“	"	``
tedunderwood-com-8283	26	9	errors	error	NNS
tedunderwood-com-8283	26	10	”	"	''
tedunderwood-com-8283	26	11	can	can	MD
tedunderwood-com-8283	26	12	be	be	VB
tedunderwood-com-8283	26	13	just	just	RB
tedunderwood-com-8283	26	14	as	as	RB
tedunderwood-com-8283	26	15	problematic	problematic	JJ
tedunderwood-com-8283	26	16	for	for	IN
tedunderwood-com-8283	26	17	diachronic	diachronic	JJ
tedunderwood-com-8283	26	18	analysis	analysis	NN
tedunderwood-com-8283	26	19	.	.	.
tedunderwood-com-8283	27	1	E.g.	e.g.	RB
tedunderwood-com-8283	27	2	,	,	,
tedunderwood-com-8283	27	3	it	-PRON-	PRP
tedunderwood-com-8283	27	4	’s	’	VBZ
tedunderwood-com-8283	27	5	a	a	DT
tedunderwood-com-8283	27	6	problem	problem	NN
tedunderwood-com-8283	27	7	that	that	IN
tedunderwood-com-8283	27	8	“	"	``
tedunderwood-com-8283	27	9	today	today	NN
tedunderwood-com-8283	27	10	”	"	''
tedunderwood-com-8283	27	11	is	be	VBZ
tedunderwood-com-8283	27	12	sometimes	sometimes	RB
tedunderwood-com-8283	27	13	written	write	VBN
tedunderwood-com-8283	27	14	“	"	``
tedunderwood-com-8283	27	15	to	to	IN
tedunderwood-com-8283	27	16	day	day	NN
tedunderwood-com-8283	27	17	”	"	''
tedunderwood-com-8283	27	18	and	and	CC
tedunderwood-com-8283	27	19	sometimes	sometimes	RB
tedunderwood-com-8283	27	20	“	"	``
tedunderwood-com-8283	27	21	to	to	IN
tedunderwood-com-8283	27	22	-	-	HYPH
tedunderwood-com-8283	27	23	day	day	NN
tedunderwood-com-8283	27	24	,	,	,
tedunderwood-com-8283	27	25	”	"	''
tedunderwood-com-8283	27	26	and	and	CC
tedunderwood-com-8283	27	27	it	-PRON-	PRP
tedunderwood-com-8283	27	28	’s	’	VBZ
tedunderwood-com-8283	27	29	a	a	DT
tedunderwood-com-8283	27	30	problem	problem	NN
tedunderwood-com-8283	27	31	that	that	IN
tedunderwood-com-8283	27	32	eighteenth	eighteenth	JJ
tedunderwood-com-8283	27	33	-	-	HYPH
tedunderwood-com-8283	27	34	century	century	NN
tedunderwood-com-8283	27	35	verbs	verb	NNS
tedunderwood-com-8283	27	36	get	get	VBP
tedunderwood-com-8283	27	37	“	"	``
tedunderwood-com-8283	27	38	condens’d	condens’d	NNP
tedunderwood-com-8283	27	39	.	.	.
tedunderwood-com-8283	27	40	”	"	''
tedunderwood-com-8283	27	41	A	a	DT
tedunderwood-com-8283	27	42	script	script	NN
tedunderwood-com-8283	27	43	designed	design	VBN
tedunderwood-com-8283	27	44	to	to	TO
tedunderwood-com-8283	27	45	correct	correct	VB
tedunderwood-com-8283	27	46	OCR	OCR	NNP
tedunderwood-com-8283	27	47	might	may	MD
tedunderwood-com-8283	27	48	leave	leave	VB
tedunderwood-com-8283	27	49	these	these	DT
tedunderwood-com-8283	27	50	variants	variant	NNS
tedunderwood-com-8283	27	51	unaltered	unaltere	VBD
tedunderwood-com-8283	27	52	,	,	,
tedunderwood-com-8283	27	53	but	but	CC
tedunderwood-com-8283	27	54	in	in	IN
tedunderwood-com-8283	27	55	order	order	NN
tedunderwood-com-8283	27	56	to	to	TO
tedunderwood-com-8283	27	57	make	make	VB
tedunderwood-com-8283	27	58	meaningful	meaningful	JJ
tedunderwood-com-8283	27	59	diachronic	diachronic	JJ
tedunderwood-com-8283	27	60	comparisons	comparison	NNS
tedunderwood-com-8283	27	61	,	,	,
tedunderwood-com-8283	27	62	I	-PRON-	PRP
tedunderwood-com-8283	27	63	have	have	VBP
tedunderwood-com-8283	27	64	to	to	TO
tedunderwood-com-8283	27	65	produce	produce	VB
tedunderwood-com-8283	27	66	a	a	DT
tedunderwood-com-8283	27	67	corpus	corpus	NN
tedunderwood-com-8283	27	68	where	where	WRB
tedunderwood-com-8283	27	69	variations	variation	NNS
tedunderwood-com-8283	27	70	of	of	IN
tedunderwood-com-8283	27	71	spelling	spelling	NN
tedunderwood-com-8283	27	72	and	and	CC
tedunderwood-com-8283	27	73	word	word	NN
tedunderwood-com-8283	27	74	division	division	NN
tedunderwood-com-8283	27	75	are	be	VBP
tedunderwood-com-8283	27	76	normalized	normalized	JJ
tedunderwood-com-8283	27	77	.	.	.
tedunderwood-com-8283	28	1	The	the	DT
tedunderwood-com-8283	28	2	rulesets	ruleset	NNS
tedunderwood-com-8283	28	3	contained	contain	VBN
tedunderwood-com-8283	28	4	in	in	IN
tedunderwood-com-8283	28	5	the	the	DT
tedunderwood-com-8283	28	6	repo	repo	NNP
tedunderwood-com-8283	28	7	standardize	standardize	NNP
tedunderwood-com-8283	28	8	(	(	-LRB-
tedunderwood-com-8283	28	9	roughly	roughly	RB
tedunderwood-com-8283	28	10	)	)	-RRB-
tedunderwood-com-8283	28	11	to	to	TO
tedunderwood-com-8283	28	12	modern	modern	JJ
tedunderwood-com-8283	28	13	British	british	JJ
tedunderwood-com-8283	28	14	practice	practice	NN
tedunderwood-com-8283	28	15	.	.	.
tedunderwood-com-8283	29	1	Some	some	DT
tedunderwood-com-8283	29	2	of	of	IN
tedunderwood-com-8283	29	3	the	the	DT
tedunderwood-com-8283	29	4	rules	rule	NNS
tedunderwood-com-8283	29	5	about	about	IN
tedunderwood-com-8283	29	6	variant	variant	JJ
tedunderwood-com-8283	29	7	spellings	spelling	NNS
tedunderwood-com-8283	29	8	were	be	VBD
tedunderwood-com-8283	29	9	originally	originally	RB
tedunderwood-com-8283	29	10	drawn	draw	VBN
tedunderwood-com-8283	29	11	,	,	,
tedunderwood-com-8283	29	12	in	in	IN
tedunderwood-com-8283	29	13	part	part	NN
tedunderwood-com-8283	29	14	,	,	,
tedunderwood-com-8283	29	15	from	from	IN
tedunderwood-com-8283	29	16	rules	rule	NNS
tedunderwood-com-8283	29	17	associated	associate	VBN
tedunderwood-com-8283	29	18	with	with	IN
tedunderwood-com-8283	29	19	the	the	DT
tedunderwood-com-8283	29	20	Wordhoard	Wordhoard	NNP
tedunderwood-com-8283	29	21	project	project	NN
tedunderwood-com-8283	29	22	,	,	,
tedunderwood-com-8283	29	23	and	and	CC
tedunderwood-com-8283	29	24	the	the	DT
tedunderwood-com-8283	29	25	some	some	DT
tedunderwood-com-8283	29	26	of	of	IN
tedunderwood-com-8283	29	27	the	the	DT
tedunderwood-com-8283	29	28	rules	rule	NNS
tedunderwood-com-8283	29	29	for	for	IN
tedunderwood-com-8283	29	30	OCR	OCR	NNP
tedunderwood-com-8283	29	31	correction	correction	NN
tedunderwood-com-8283	29	32	were	be	VBD
tedunderwood-com-8283	29	33	developed	develop	VBN
tedunderwood-com-8283	29	34	in	in	IN
tedunderwood-com-8283	29	35	collaboration	collaboration	NN
tedunderwood-com-8283	29	36	with	with	IN
tedunderwood-com-8283	29	37	Loretta	Loretta	NNP
tedunderwood-com-8283	29	38	Auvil	Auvil	NNP
tedunderwood-com-8283	29	39	.	.	.
tedunderwood-com-8283	30	1	Subfolders	subfolder	NNS
tedunderwood-com-8283	30	2	of	of	IN
tedunderwood-com-8283	30	3	the	the	DT
tedunderwood-com-8283	30	4	repo	repo	NNP
tedunderwood-com-8283	30	5	contain	contain	NN
tedunderwood-com-8283	30	6	scripts	script	NNS
tedunderwood-com-8283	30	7	I	-PRON-	PRP
tedunderwood-com-8283	30	8	used	use	VBD
tedunderwood-com-8283	30	9	to	to	TO
tedunderwood-com-8283	30	10	develop	develop	VB
tedunderwood-com-8283	30	11	new	new	JJ
tedunderwood-com-8283	30	12	rules	rule	NNS
tedunderwood-com-8283	30	13	.	.	.
tedunderwood-com-8283	31	1	I	-PRON-	PRP
tedunderwood-com-8283	31	2	’ve	have	VB
tedunderwood-com-8283	31	3	called	call	VBN
tedunderwood-com-8283	31	4	this	this	DT
tedunderwood-com-8283	31	5	release	release	NN
tedunderwood-com-8283	31	6	version	version	NN
tedunderwood-com-8283	31	7	0.1	0.1	CD
tedunderwood-com-8283	31	8	because	because	IN
tedunderwood-com-8283	31	9	it	-PRON-	PRP
tedunderwood-com-8283	31	10	’s	’	VBZ
tedunderwood-com-8283	31	11	very	very	RB
tedunderwood-com-8283	31	12	rough	rough	JJ
tedunderwood-com-8283	31	13	.	.	.
tedunderwood-com-8283	32	1	You	-PRON-	PRP
tedunderwood-com-8283	32	2	can	can	MD
tedunderwood-com-8283	32	3	write	write	VB
tedunderwood-com-8283	32	4	Python	Python	NNP
tedunderwood-com-8283	32	5	in	in	IN
tedunderwood-com-8283	32	6	a	a	DT
tedunderwood-com-8283	32	7	disciplined	discipline	VBN
tedunderwood-com-8283	32	8	,	,	,
tedunderwood-com-8283	32	9	object	object	NN
tedunderwood-com-8283	32	10	-	-	HYPH
tedunderwood-com-8283	32	11	oriented	orient	VBN
tedunderwood-com-8283	32	12	way	way	NN
tedunderwood-com-8283	32	13	…	…	NFP
tedunderwood-com-8283	32	14	but	but	CC
tedunderwood-com-8283	32	15	I	-PRON-	PRP
tedunderwood-com-8283	32	16	,	,	,
tedunderwood-com-8283	32	17	um	um	UH
tedunderwood-com-8283	32	18	,	,	,
tedunderwood-com-8283	32	19	tend	tend	VB
tedunderwood-com-8283	32	20	not	not	RB
tedunderwood-com-8283	32	21	to	to	TO
tedunderwood-com-8283	32	22	.	.	.
tedunderwood-com-8283	33	1	This	this	DT
tedunderwood-com-8283	33	2	code	code	NN
tedunderwood-com-8283	33	3	has	have	VBZ
tedunderwood-com-8283	33	4	grown	grow	VBN
tedunderwood-com-8283	33	5	by	by	IN
tedunderwood-com-8283	33	6	accretion	accretion	NN
tedunderwood-com-8283	33	7	,	,	,
tedunderwood-com-8283	33	8	and	and	CC
tedunderwood-com-8283	33	9	I	-PRON-	PRP
tedunderwood-com-8283	33	10	’m	be	VBP
tedunderwood-com-8283	33	11	sure	sure	JJ
tedunderwood-com-8283	33	12	there	there	EX
tedunderwood-com-8283	33	13	are	be	VBP
tedunderwood-com-8283	33	14	bugs	bug	NNS
tedunderwood-com-8283	33	15	.	.	.
tedunderwood-com-8283	34	1	More	more	RBR
tedunderwood-com-8283	34	2	importantly	importantly	RB
tedunderwood-com-8283	34	3	,	,	,
tedunderwood-com-8283	34	4	as	as	IN
tedunderwood-com-8283	34	5	noted	note	VBN
tedunderwood-com-8283	34	6	above	above	IN
tedunderwood-com-8283	34	7	,	,	,
tedunderwood-com-8283	34	8	this	this	DT
tedunderwood-com-8283	34	9	is	be	VBZ
tedunderwood-com-8283	34	10	n’t	not	RB
tedunderwood-com-8283	34	11	a	a	DT
tedunderwood-com-8283	34	12	generic	generic	JJ
tedunderwood-com-8283	34	13	“	"	``
tedunderwood-com-8283	34	14	corrector	corrector	NN
tedunderwood-com-8283	34	15	”	"	''
tedunderwood-com-8283	34	16	but	but	CC
tedunderwood-com-8283	34	17	a	a	DT
tedunderwood-com-8283	34	18	script	script	NN
tedunderwood-com-8283	34	19	that	that	WDT
tedunderwood-com-8283	34	20	normalizes	normalize	VBZ
tedunderwood-com-8283	34	21	in	in	IN
tedunderwood-com-8283	34	22	order	order	NN
tedunderwood-com-8283	34	23	to	to	TO
tedunderwood-com-8283	34	24	permit	permit	VB
tedunderwood-com-8283	34	25	diachronic	diachronic	JJ
tedunderwood-com-8283	34	26	comparison	comparison	NN
tedunderwood-com-8283	34	27	.	.	.
tedunderwood-com-8283	35	1	It	-PRON-	PRP
tedunderwood-com-8283	35	2	wo	will	MD
tedunderwood-com-8283	35	3	n’t	not	RB
tedunderwood-com-8283	35	4	meet	meet	VB
tedunderwood-com-8283	35	5	everyone	everyone	NN
tedunderwood-com-8283	35	6	’s	’s	POS
tedunderwood-com-8283	35	7	needs	need	VBZ
tedunderwood-com-8283	35	8	.	.	.
tedunderwood-com-8283	36	1	But	but	CC
tedunderwood-com-8283	36	2	there	there	EX
tedunderwood-com-8283	36	3	may	may	MD
tedunderwood-com-8283	36	4	be	be	VB
tedunderwood-com-8283	36	5	a	a	DT
tedunderwood-com-8283	36	6	few	few	JJ
tedunderwood-com-8283	36	7	projects	project	NNS
tedunderwood-com-8283	36	8	out	out	IN
tedunderwood-com-8283	36	9	there	there	RB
tedunderwood-com-8283	36	10	that	that	WDT
tedunderwood-com-8283	36	11	would	would	MD
tedunderwood-com-8283	36	12	find	find	VB
tedunderwood-com-8283	36	13	it	-PRON-	PRP
tedunderwood-com-8283	36	14	useful	useful	JJ
tedunderwood-com-8283	36	15	as	as	IN
tedunderwood-com-8283	36	16	a	a	DT
tedunderwood-com-8283	36	17	resource	resource	NN
tedunderwood-com-8283	36	18	—	—	:
tedunderwood-com-8283	36	19	if	if	IN
tedunderwood-com-8283	36	20	so	so	RB
tedunderwood-com-8283	36	21	,	,	,
tedunderwood-com-8283	36	22	feel	feel	VB
tedunderwood-com-8283	36	23	free	free	JJ
tedunderwood-com-8283	36	24	to	to	TO
tedunderwood-com-8283	36	25	fork	fork	VB
tedunderwood-com-8283	36	26	it	-PRON-	PRP
tedunderwood-com-8283	36	27	and	and	CC
tedunderwood-com-8283	36	28	alter	alter	VB
tedunderwood-com-8283	36	29	it	-PRON-	PRP
tedunderwood-com-8283	36	30	to	to	TO
tedunderwood-com-8283	36	31	fit	fit	VB
tedunderwood-com-8283	36	32	your	-PRON-	PRP$
tedunderwood-com-8283	36	33	project	project	NN
tedunderwood-com-8283	36	34	!	!	.
tedunderwood-com-8283	37	1	Share	share	VB
tedunderwood-com-8283	37	2	this	this	DT
tedunderwood-com-8283	37	3	:	:	:
tedunderwood-com-8283	37	4	Twitter	Twitter	NNP
tedunderwood-com-8283	37	5	Like	like	IN
tedunderwood-com-8283	37	6	this	this	DT
tedunderwood-com-8283	37	7	:	:	:
tedunderwood-com-8283	37	8	Like	like	IN
tedunderwood-com-8283	37	9	Loading	Loading	NNP
tedunderwood-com-8283	37	10	...	...	.
tedunderwood-com-8283	37	11	Related	relate	VBN
tedunderwood-com-8283	37	12	This	this	DT
tedunderwood-com-8283	37	13	entry	entry	NN
tedunderwood-com-8283	37	14	was	be	VBD
tedunderwood-com-8283	37	15	posted	post	VBN
tedunderwood-com-8283	37	16	in	in	IN
tedunderwood-com-8283	37	17	collection	collection	NN
tedunderwood-com-8283	37	18	-	-	HYPH
tedunderwood-com-8283	37	19	building	building	NN
tedunderwood-com-8283	37	20	,	,	,
tedunderwood-com-8283	37	21	OCR	ocr	NN
tedunderwood-com-8283	37	22	correction	correction	NN
tedunderwood-com-8283	37	23	by	by	IN
tedunderwood-com-8283	37	24	tedunderwood	tedunderwood	NN
tedunderwood-com-8283	37	25	.	.	.
tedunderwood-com-8283	38	1	Bookmark	bookmark	VB
tedunderwood-com-8283	38	2	the	the	DT
tedunderwood-com-8283	38	3	permalink	permalink	NN
tedunderwood-com-8283	38	4	.	.	.
tedunderwood-com-8283	39	1	About	about	IN
tedunderwood-com-8283	39	2	tedunderwood	tedunderwood	NN
tedunderwood-com-8283	39	3	Ted	Ted	NNP
tedunderwood-com-8283	39	4	Underwood	Underwood	NNP
tedunderwood-com-8283	39	5	is	be	VBZ
tedunderwood-com-8283	39	6	Professor	Professor	NNP
tedunderwood-com-8283	39	7	of	of	IN
tedunderwood-com-8283	39	8	Information	Information	NNP
tedunderwood-com-8283	39	9	Sciences	Sciences	NNPS
tedunderwood-com-8283	39	10	and	and	CC
tedunderwood-com-8283	39	11	English	English	NNP
tedunderwood-com-8283	39	12	at	at	IN
tedunderwood-com-8283	39	13	the	the	DT
tedunderwood-com-8283	39	14	University	University	NNP
tedunderwood-com-8283	39	15	of	of	IN
tedunderwood-com-8283	39	16	Illinois	Illinois	NNP
tedunderwood-com-8283	39	17	,	,	,
tedunderwood-com-8283	39	18	Urbana	Urbana	NNP
tedunderwood-com-8283	39	19	-	-	HYPH
tedunderwood-com-8283	39	20	Champaign	Champaign	NNP
tedunderwood-com-8283	39	21	.	.	.
tedunderwood-com-8283	40	1	On	on	IN
tedunderwood-com-8283	40	2	Twitter	Twitter	NNP
tedunderwood-com-8283	40	3	he	-PRON-	PRP
tedunderwood-com-8283	40	4	is	be	VBZ
tedunderwood-com-8283	40	5	@Ted_Underwood	@ted_underwood	NN
tedunderwood-com-8283	40	6	.	.	.
tedunderwood-com-8283	41	1	View	view	VB
tedunderwood-com-8283	41	2	all	all	DT
tedunderwood-com-8283	41	3	posts	post	NNS
tedunderwood-com-8283	41	4	by	by	IN
tedunderwood-com-8283	41	5	tedunderwood	tedunderwood	NN
tedunderwood-com-8283	41	6	→	→	SYM
tedunderwood-com-8283	41	7	8	8	CD
tedunderwood-com-8283	41	8	thoughts	thought	NNS
tedunderwood-com-8283	41	9	on	on	IN
tedunderwood-com-8283	41	10	“	"	``
tedunderwood-com-8283	41	11	A	a	DT
tedunderwood-com-8283	41	12	half	half	JJ
tedunderwood-com-8283	41	13	-	-	HYPH
tedunderwood-com-8283	41	14	decent	decent	JJ
tedunderwood-com-8283	41	15	OCR	ocr	NN
tedunderwood-com-8283	41	16	normalizer	normalizer	NN
tedunderwood-com-8283	41	17	for	for	IN
tedunderwood-com-8283	41	18	English	English	NNP
tedunderwood-com-8283	41	19	texts	text	NNS
tedunderwood-com-8283	41	20	after	after	IN
tedunderwood-com-8283	41	21	 	  	_SP
tedunderwood-com-8283	41	22	1700	1700	CD
tedunderwood-com-8283	41	23	.	.	.
tedunderwood-com-8283	41	24	”	"	''
tedunderwood-com-8283	41	25	Pingback	Pingback	NNP
tedunderwood-com-8283	41	26	:	:	:
tedunderwood-com-8283	41	27	Resource	resource	NN
tedunderwood-com-8283	41	28	:	:	:
tedunderwood-com-8283	41	29	An	an	DT
tedunderwood-com-8283	41	30	OCR	ocr	NN
tedunderwood-com-8283	41	31	normalizer	normalizer	NN
tedunderwood-com-8283	41	32	for	for	IN
tedunderwood-com-8283	41	33	English	English	NNP
tedunderwood-com-8283	41	34	texts	text	NNS
tedunderwood-com-8283	41	35	after	after	IN
tedunderwood-com-8283	41	36	1700	1700	CD
tedunderwood-com-8283	41	37	|	|	NNP
tedunderwood-com-8283	41	38	Digital	Digital	NNP
tedunderwood-com-8283	41	39	Humanities	Humanities	NNPS
tedunderwood-com-8283	41	40	Now	now	RB
tedunderwood-com-8283	41	41	Martin	Martin	NNP
tedunderwood-com-8283	41	42	Reynaert	Reynaert	NNP
tedunderwood-com-8283	41	43	on	on	IN
tedunderwood-com-8283	41	44	December	December	NNP
tedunderwood-com-8283	41	45	13	13	CD
tedunderwood-com-8283	41	46	,	,	,
tedunderwood-com-8283	41	47	2013	2013	CD
tedunderwood-com-8283	41	48	at	at	IN
tedunderwood-com-8283	41	49	8:30	8:30	CD
tedunderwood-com-8283	41	50	am	am	NN
tedunderwood-com-8283	41	51	said	say	VBN
tedunderwood-com-8283	41	52	:	:	:
tedunderwood-com-8283	41	53	Dear	Dear	NNP
tedunderwood-com-8283	41	54	Ted	Ted	NNP
tedunderwood-com-8283	41	55	,	,	,
tedunderwood-com-8283	41	56	Thank	thank	VBP
tedunderwood-com-8283	41	57	you	-PRON-	PRP
tedunderwood-com-8283	41	58	for	for	IN
tedunderwood-com-8283	41	59	this	this	DT
tedunderwood-com-8283	41	60	blog	blog	NN
tedunderwood-com-8283	41	61	!	!	.
tedunderwood-com-8283	42	1	It	-PRON-	PRP
tedunderwood-com-8283	42	2	is	be	VBZ
tedunderwood-com-8283	42	3	with	with	IN
tedunderwood-com-8283	42	4	great	great	JJ
tedunderwood-com-8283	42	5	pleasure	pleasure	NN
tedunderwood-com-8283	42	6	that	that	WDT
tedunderwood-com-8283	42	7	I	-PRON-	PRP
tedunderwood-com-8283	42	8	learn	learn	VBP
tedunderwood-com-8283	42	9	I	-PRON-	PRP
tedunderwood-com-8283	42	10	am	be	VBP
tedunderwood-com-8283	42	11	not	not	RB
tedunderwood-com-8283	42	12	the	the	DT
tedunderwood-com-8283	42	13	sole	sole	JJ
tedunderwood-com-8283	42	14	person	person	NN
tedunderwood-com-8283	42	15	in	in	IN
tedunderwood-com-8283	42	16	the	the	DT
tedunderwood-com-8283	42	17	world	world	NN
tedunderwood-com-8283	42	18	to	to	TO
tedunderwood-com-8283	42	19	attempt	attempt	VB
tedunderwood-com-8283	42	20	to	to	TO
tedunderwood-com-8283	42	21	clean	clean	VB
tedunderwood-com-8283	42	22	up	up	RP
tedunderwood-com-8283	42	23	or	or	CC
tedunderwood-com-8283	42	24	normalize	normalize	VB
tedunderwood-com-8283	42	25	collections	collection	NNS
tedunderwood-com-8283	42	26	of	of	IN
tedunderwood-com-8283	42	27	digitized	digitized	JJ
tedunderwood-com-8283	42	28	texts	text	NNS
tedunderwood-com-8283	42	29	.	.	.
tedunderwood-com-8283	43	1	The	the	DT
tedunderwood-com-8283	43	2	main	main	JJ
tedunderwood-com-8283	43	3	paper	paper	NN
tedunderwood-com-8283	43	4	describing	describe	VBG
tedunderwood-com-8283	43	5	my	-PRON-	PRP$
tedunderwood-com-8283	43	6	efforts	effort	NNS
tedunderwood-com-8283	43	7	is	be	VBZ
tedunderwood-com-8283	43	8	here	here	RB
tedunderwood-com-8283	43	9	,	,	,
tedunderwood-com-8283	43	10	in	in	IN
tedunderwood-com-8283	43	11	Open	open	JJ
tedunderwood-com-8283	43	12	Access	access	NN
tedunderwood-com-8283	43	13	:	:	:
tedunderwood-com-8283	43	14	http://link.springer.com/article/10.1007%2Fs10032-010-0133-5#page-1	http://link.springer.com/article/10.1007%2fs10032-010-0133-5#page-1	ADD
tedunderwood-com-8283	43	15	The	the	DT
tedunderwood-com-8283	43	16	problem	problem	NN
tedunderwood-com-8283	43	17	of	of	IN
tedunderwood-com-8283	43	18	evaluating	evaluate	VBG
tedunderwood-com-8283	43	19	one	one	NN
tedunderwood-com-8283	43	20	’s	’s	NN
tedunderwood-com-8283	43	21	attempts	attempt	NNS
tedunderwood-com-8283	43	22	has	have	VBZ
tedunderwood-com-8283	43	23	fascinated	fascinate	VBN
tedunderwood-com-8283	43	24	(	(	-LRB-
tedunderwood-com-8283	43	25	and	and	CC
tedunderwood-com-8283	43	26	frustrated	frustrate	VBN
tedunderwood-com-8283	43	27	at	at	IN
tedunderwood-com-8283	43	28	times	time	NNS
tedunderwood-com-8283	43	29	)	)	-RRB-
tedunderwood-com-8283	43	30	me	-PRON-	PRP
tedunderwood-com-8283	43	31	for	for	IN
tedunderwood-com-8283	43	32	years	year	NNS
tedunderwood-com-8283	43	33	(	(	-LRB-
tedunderwood-com-8283	43	34	cf	cf	NN
tedunderwood-com-8283	43	35	.	.	.
tedunderwood-com-8283	44	1	http://www.lrec-conf.org/proceedings/lrec2008/summaries/477.html	http://www.lrec-conf.org/proceedings/lrec2008/summaries/477.html	NN
tedunderwood-com-8283	44	2	)	)	-RRB-
tedunderwood-com-8283	44	3	.	.	.
tedunderwood-com-8283	45	1	I	-PRON-	PRP
tedunderwood-com-8283	45	2	do	do	VBP
tedunderwood-com-8283	45	3	think	think	VB
tedunderwood-com-8283	45	4	you	-PRON-	PRP
tedunderwood-com-8283	45	5	have	have	VBP
tedunderwood-com-8283	45	6	chosen	choose	VBN
tedunderwood-com-8283	45	7	the	the	DT
tedunderwood-com-8283	45	8	words	word	NNS
tedunderwood-com-8283	45	9	in	in	IN
tedunderwood-com-8283	45	10	your	-PRON-	PRP$
tedunderwood-com-8283	45	11	title	title	NN
tedunderwood-com-8283	45	12	very	very	RB
tedunderwood-com-8283	45	13	carefully	carefully	RB
tedunderwood-com-8283	45	14	.	.	.
tedunderwood-com-8283	46	1	But	but	CC
tedunderwood-com-8283	46	2	for	for	IN
tedunderwood-com-8283	46	3	me	-PRON-	PRP
tedunderwood-com-8283	46	4	to	to	TO
tedunderwood-com-8283	46	5	properly	properly	RB
tedunderwood-com-8283	46	6	appraise	appraise	VB
tedunderwood-com-8283	46	7	them	-PRON-	PRP
tedunderwood-com-8283	46	8	I	-PRON-	PRP
tedunderwood-com-8283	46	9	have	have	VBP
tedunderwood-com-8283	46	10	to	to	TO
tedunderwood-com-8283	46	11	ask	ask	VB
tedunderwood-com-8283	46	12	you	-PRON-	PRP
tedunderwood-com-8283	46	13	to	to	TO
tedunderwood-com-8283	46	14	elucidate	elucidate	VB
tedunderwood-com-8283	46	15	a	a	DT
tedunderwood-com-8283	46	16	few	few	JJ
tedunderwood-com-8283	46	17	points	point	NNS
tedunderwood-com-8283	46	18	about	about	IN
tedunderwood-com-8283	46	19	the	the	DT
tedunderwood-com-8283	46	20	graph	graph	NN
tedunderwood-com-8283	46	21	you	-PRON-	PRP
tedunderwood-com-8283	46	22	provide	provide	VBP
tedunderwood-com-8283	46	23	.	.	.
tedunderwood-com-8283	47	1	The	the	DT
tedunderwood-com-8283	47	2	caption	caption	NN
tedunderwood-com-8283	47	3	to	to	IN
tedunderwood-com-8283	47	4	your	-PRON-	PRP$
tedunderwood-com-8283	47	5	graph	graph	NN
tedunderwood-com-8283	47	6	states	state	NNS
tedunderwood-com-8283	47	7	“	"	``
tedunderwood-com-8283	47	8	The	the	DT
tedunderwood-com-8283	47	9	percentage	percentage	NN
tedunderwood-com-8283	47	10	of	of	IN
tedunderwood-com-8283	47	11	tokens	token	NNS
tedunderwood-com-8283	47	12	in	in	IN
tedunderwood-com-8283	47	13	the	the	DT
tedunderwood-com-8283	47	14	HathiTrust	HathiTrust	NNP
tedunderwood-com-8283	47	15	corpus	corpus	NN
tedunderwood-com-8283	47	16	that	that	WDT
tedunderwood-com-8283	47	17	are	be	VBP
tedunderwood-com-8283	47	18	recognized	recognize	VBN
tedunderwood-com-8283	47	19	as	as	IN
tedunderwood-com-8283	47	20	words	word	NNS
tedunderwood-com-8283	47	21	”	"	''
tedunderwood-com-8283	47	22	.	.	.
tedunderwood-com-8283	48	1	What	what	WP
tedunderwood-com-8283	48	2	exactly	exactly	RB
tedunderwood-com-8283	48	3	does	do	VBZ
tedunderwood-com-8283	48	4	each	each	DT
tedunderwood-com-8283	48	5	data	data	NN
tedunderwood-com-8283	48	6	point	point	NN
tedunderwood-com-8283	48	7	in	in	IN
tedunderwood-com-8283	48	8	the	the	DT
tedunderwood-com-8283	48	9	graph	graph	NN
tedunderwood-com-8283	48	10	represent	represent	NN
tedunderwood-com-8283	48	11	?	?	.
tedunderwood-com-8283	49	1	Is	be	VBZ
tedunderwood-com-8283	49	2	it	-PRON-	PRP
tedunderwood-com-8283	49	3	the	the	DT
tedunderwood-com-8283	49	4	cumulative	cumulative	JJ
tedunderwood-com-8283	49	5	result	result	NN
tedunderwood-com-8283	49	6	of	of	IN
tedunderwood-com-8283	49	7	your	-PRON-	PRP$
tedunderwood-com-8283	49	8	system	system	NN
tedunderwood-com-8283	49	9	’s	’s	POS
tedunderwood-com-8283	49	10	achievements	achievement	NNS
tedunderwood-com-8283	49	11	on	on	IN
tedunderwood-com-8283	49	12	perhaps	perhaps	RB
tedunderwood-com-8283	49	13	one	one	CD
tedunderwood-com-8283	49	14	book	book	NN
tedunderwood-com-8283	49	15	published	publish	VBN
tedunderwood-com-8283	49	16	in	in	IN
tedunderwood-com-8283	49	17	the	the	DT
tedunderwood-com-8283	49	18	particular	particular	JJ
tedunderwood-com-8283	49	19	year	year	NN
tedunderwood-com-8283	49	20	?	?	.
tedunderwood-com-8283	50	1	Or	or	CC
tedunderwood-com-8283	50	2	is	be	VBZ
tedunderwood-com-8283	50	3	this	this	DT
tedunderwood-com-8283	50	4	on	on	IN
tedunderwood-com-8283	50	5	all	all	PDT
tedunderwood-com-8283	50	6	the	the	DT
tedunderwood-com-8283	50	7	Hathi	Hathi	NNP
tedunderwood-com-8283	50	8	books	book	NNS
tedunderwood-com-8283	50	9	in	in	IN
tedunderwood-com-8283	50	10	English	English	NNP
tedunderwood-com-8283	50	11	?	?	.
tedunderwood-com-8283	51	1	I	-PRON-	PRP
tedunderwood-com-8283	51	2	have	have	VBP
tedunderwood-com-8283	51	3	recently	recently	RB
tedunderwood-com-8283	51	4	had	have	VBN
tedunderwood-com-8283	51	5	occasion	occasion	NN
tedunderwood-com-8283	51	6	to	to	TO
tedunderwood-com-8283	51	7	take	take	VB
tedunderwood-com-8283	51	8	a	a	DT
tedunderwood-com-8283	51	9	closer	close	JJR
tedunderwood-com-8283	51	10	look	look	NN
tedunderwood-com-8283	51	11	at	at	IN
tedunderwood-com-8283	51	12	the	the	DT
tedunderwood-com-8283	51	13	Hathi	Hathi	NNP
tedunderwood-com-8283	51	14	collections	collection	NNS
tedunderwood-com-8283	51	15	and	and	CC
tedunderwood-com-8283	51	16	a	a	DT
tedunderwood-com-8283	51	17	lot	lot	NN
tedunderwood-com-8283	51	18	of	of	IN
tedunderwood-com-8283	51	19	books	book	NNS
tedunderwood-com-8283	51	20	seemed	seem	VBD
tedunderwood-com-8283	51	21	not	not	RB
tedunderwood-com-8283	51	22	accessible	accessible	JJ
tedunderwood-com-8283	51	23	.	.	.
tedunderwood-com-8283	52	1	Also	also	RB
tedunderwood-com-8283	52	2	,	,	,
tedunderwood-com-8283	52	3	how	how	WRB
tedunderwood-com-8283	52	4	do	do	VBP
tedunderwood-com-8283	52	5	you	-PRON-	PRP
tedunderwood-com-8283	52	6	determine	determine	VB
tedunderwood-com-8283	52	7	a	a	DT
tedunderwood-com-8283	52	8	word	word	NN
tedunderwood-com-8283	52	9	is	be	VBZ
tedunderwood-com-8283	52	10	correct	correct	JJ
tedunderwood-com-8283	52	11	?	?	.
tedunderwood-com-8283	53	1	Is	be	VBZ
tedunderwood-com-8283	53	2	this	this	DT
tedunderwood-com-8283	53	3	in	in	IN
tedunderwood-com-8283	53	4	reference	reference	NN
tedunderwood-com-8283	53	5	to	to	IN
tedunderwood-com-8283	53	6	a	a	DT
tedunderwood-com-8283	53	7	validated	validated	JJ
tedunderwood-com-8283	53	8	lexicon	lexicon	NN
tedunderwood-com-8283	53	9	?	?	.
tedunderwood-com-8283	54	1	Is	be	VBZ
tedunderwood-com-8283	54	2	this	this	DT
tedunderwood-com-8283	54	3	lexicon	lexicon	NN
tedunderwood-com-8283	54	4	perhaps	perhaps	RB
tedunderwood-com-8283	54	5	available	available	JJ
tedunderwood-com-8283	54	6	?	?	.
tedunderwood-com-8283	55	1	Sure	sure	UH
tedunderwood-com-8283	55	2	what	what	WP
tedunderwood-com-8283	55	3	is	be	VBZ
tedunderwood-com-8283	55	4	correct	correct	JJ
tedunderwood-com-8283	55	5	or	or	CC
tedunderwood-com-8283	55	6	not	not	RB
tedunderwood-com-8283	55	7	depends	depend	VBZ
tedunderwood-com-8283	55	8	on	on	IN
tedunderwood-com-8283	55	9	the	the	DT
tedunderwood-com-8283	55	10	coverage	coverage	NN
tedunderwood-com-8283	55	11	of	of	IN
tedunderwood-com-8283	55	12	the	the	DT
tedunderwood-com-8283	55	13	lexicon	lexicon	NN
tedunderwood-com-8283	55	14	one	one	CD
tedunderwood-com-8283	55	15	uses	use	VBZ
tedunderwood-com-8283	55	16	?	?	.
tedunderwood-com-8283	56	1	Or	or	CC
tedunderwood-com-8283	56	2	do	do	VBP
tedunderwood-com-8283	56	3	you	-PRON-	PRP
tedunderwood-com-8283	56	4	actually	actually	RB
tedunderwood-com-8283	56	5	have	have	VB
tedunderwood-com-8283	56	6	OCR	ocr	NN
tedunderwood-com-8283	56	7	ground	ground	NN
tedunderwood-com-8283	56	8	truths	truth	NNS
tedunderwood-com-8283	56	9	or	or	CC
tedunderwood-com-8283	56	10	OCR	ocr	NN
tedunderwood-com-8283	56	11	post	post	JJ
tedunderwood-com-8283	56	12	-	-	JJ
tedunderwood-com-8283	56	13	correction	correction	JJ
tedunderwood-com-8283	56	14	gold	gold	NN
tedunderwood-com-8283	56	15	standards	standard	NNS
tedunderwood-com-8283	56	16	for	for	IN
tedunderwood-com-8283	56	17	so	so	RB
tedunderwood-com-8283	56	18	many	many	JJ
tedunderwood-com-8283	56	19	books	book	NNS
tedunderwood-com-8283	56	20	?	?	.
tedunderwood-com-8283	57	1	I	-PRON-	PRP
tedunderwood-com-8283	57	2	do	do	VBP
tedunderwood-com-8283	57	3	not	not	RB
tedunderwood-com-8283	57	4	quite	quite	RB
tedunderwood-com-8283	57	5	see	see	VB
tedunderwood-com-8283	57	6	how	how	WRB
tedunderwood-com-8283	57	7	else	else	RB
tedunderwood-com-8283	57	8	one	one	PRP
tedunderwood-com-8283	57	9	can	can	MD
tedunderwood-com-8283	57	10	evaluate	evaluate	VB
tedunderwood-com-8283	57	11	whether	whether	IN
tedunderwood-com-8283	57	12	a	a	DT
tedunderwood-com-8283	57	13	word	word	NN
tedunderwood-com-8283	57	14	in	in	IN
tedunderwood-com-8283	57	15	context	context	NN
tedunderwood-com-8283	57	16	(	(	-LRB-
tedunderwood-com-8283	57	17	‘	'	``
tedunderwood-com-8283	57	18	it	-PRON-	PRP
tedunderwood-com-8283	57	19	uses	use	VBZ
tedunderwood-com-8283	57	20	the	the	DT
tedunderwood-com-8283	57	21	words	word	NNS
tedunderwood-com-8283	57	22	on	on	IN
tedunderwood-com-8283	57	23	either	either	DT
tedunderwood-com-8283	57	24	side	side	NN
tedunderwood-com-8283	57	25	to	to	TO
tedunderwood-com-8283	57	26	disambiguate	disambiguate	VB
tedunderwood-com-8283	57	27	’	'	''
tedunderwood-com-8283	57	28	)	)	-RRB-
tedunderwood-com-8283	57	29	was	be	VBD
tedunderwood-com-8283	57	30	properly	properly	RB
tedunderwood-com-8283	57	31	corrected	correct	VBN
tedunderwood-com-8283	57	32	.	.	.
tedunderwood-com-8283	58	1	Would	Would	MD
tedunderwood-com-8283	58	2	these	these	DT
tedunderwood-com-8283	58	3	ground	ground	NN
tedunderwood-com-8283	58	4	truths	truth	NNS
tedunderwood-com-8283	58	5	then	then	RB
tedunderwood-com-8283	58	6	be	be	VB
tedunderwood-com-8283	58	7	available	available	JJ
tedunderwood-com-8283	58	8	to	to	IN
tedunderwood-com-8283	58	9	others	other	NNS
tedunderwood-com-8283	58	10	for	for	IN
tedunderwood-com-8283	58	11	research	research	NN
tedunderwood-com-8283	58	12	?	?	.
tedunderwood-com-8283	59	1	Thank	thank	VBP
tedunderwood-com-8283	59	2	you	-PRON-	PRP
tedunderwood-com-8283	59	3	for	for	IN
tedunderwood-com-8283	59	4	sharing	share	VBG
tedunderwood-com-8283	59	5	your	-PRON-	PRP$
tedunderwood-com-8283	59	6	tool	tool	NN
tedunderwood-com-8283	59	7	!	!	.
tedunderwood-com-8283	60	1	I	-PRON-	PRP
tedunderwood-com-8283	60	2	will	will	MD
tedunderwood-com-8283	60	3	definitely	definitely	RB
tedunderwood-com-8283	60	4	try	try	VB
tedunderwood-com-8283	60	5	it	-PRON-	PRP
tedunderwood-com-8283	60	6	.	.	.
tedunderwood-com-8283	61	1	Looking	look	VBG
tedunderwood-com-8283	61	2	forward	forward	RB
tedunderwood-com-8283	61	3	for	for	IN
tedunderwood-com-8283	61	4	any	any	DT
tedunderwood-com-8283	61	5	additional	additional	JJ
tedunderwood-com-8283	61	6	information	information	NN
tedunderwood-com-8283	61	7	you	-PRON-	PRP
tedunderwood-com-8283	61	8	can	can	MD
tedunderwood-com-8283	61	9	give	give	VB
tedunderwood-com-8283	61	10	!	!	.
tedunderwood-com-8283	62	1	Best	good	JJS
tedunderwood-com-8283	62	2	regards	regard	NNS
tedunderwood-com-8283	62	3	,	,	,
tedunderwood-com-8283	62	4	Martin	Martin	NNP
tedunderwood-com-8283	62	5	Reynaert	Reynaert	NNP
tedunderwood-com-8283	62	6	Postdoc	Postdoc	NNP
tedunderwood-com-8283	62	7	Researcher	Researcher	NNP
tedunderwood-com-8283	62	8	TiCC	TiCC	NNP
tedunderwood-com-8283	62	9	–	–	:
tedunderwood-com-8283	62	10	Tilburg	Tilburg	NNP
tedunderwood-com-8283	62	11	University	University	NNP
tedunderwood-com-8283	62	12	CSLT	CSLT	NNP
tedunderwood-com-8283	62	13	–	–	:
tedunderwood-com-8283	62	14	Radboud	Radboud	NNP
tedunderwood-com-8283	62	15	University	University	NNP
tedunderwood-com-8283	62	16	The	the	DT
tedunderwood-com-8283	62	17	Netherlands	Netherlands	NNP
tedunderwood-com-8283	62	18	Reply	Reply	NNP
tedunderwood-com-8283	62	19	↓	↓	NNP
tedunderwood-com-8283	62	20	tedunderwood	tedunderwood	NN
tedunderwood-com-8283	62	21	on	on	IN
tedunderwood-com-8283	62	22	December	December	NNP
tedunderwood-com-8283	62	23	13	13	CD
tedunderwood-com-8283	62	24	,	,	,
tedunderwood-com-8283	62	25	2013	2013	CD
tedunderwood-com-8283	62	26	at	at	IN
tedunderwood-com-8283	62	27	12:56	12:56	CD
tedunderwood-com-8283	62	28	pm	pm	NN
tedunderwood-com-8283	62	29	said	say	VBD
tedunderwood-com-8283	62	30	:	:	:
tedunderwood-com-8283	62	31	Hi	hi	UH
tedunderwood-com-8283	62	32	Martin	Martin	NNP
tedunderwood-com-8283	62	33	—	—	:
tedunderwood-com-8283	62	34	Thanks	thank	NNS
tedunderwood-com-8283	62	35	for	for	IN
tedunderwood-com-8283	62	36	those	those	DT
tedunderwood-com-8283	62	37	links	link	NNS
tedunderwood-com-8283	62	38	.	.	.
tedunderwood-com-8283	63	1	I	-PRON-	PRP
tedunderwood-com-8283	63	2	’m	be	VBP
tedunderwood-com-8283	63	3	collaborating	collaborate	VBG
tedunderwood-com-8283	63	4	with	with	IN
tedunderwood-com-8283	63	5	a	a	DT
tedunderwood-com-8283	63	6	couple	couple	NN
tedunderwood-com-8283	63	7	of	of	IN
tedunderwood-com-8283	63	8	other	other	JJ
tedunderwood-com-8283	63	9	people	people	NNS
tedunderwood-com-8283	63	10	on	on	IN
tedunderwood-com-8283	63	11	the	the	DT
tedunderwood-com-8283	63	12	problem	problem	NN
tedunderwood-com-8283	63	13	of	of	IN
tedunderwood-com-8283	63	14	OCR	ocr	NN
tedunderwood-com-8283	63	15	evaluation	evaluation	NN
tedunderwood-com-8283	63	16	,	,	,
tedunderwood-com-8283	63	17	and	and	CC
tedunderwood-com-8283	63	18	these	these	DT
tedunderwood-com-8283	63	19	leads	lead	NNS
tedunderwood-com-8283	63	20	will	will	MD
tedunderwood-com-8283	63	21	be	be	VB
tedunderwood-com-8283	63	22	very	very	RB
tedunderwood-com-8283	63	23	helpful	helpful	JJ
tedunderwood-com-8283	63	24	.	.	.
tedunderwood-com-8283	64	1	The	the	DT
tedunderwood-com-8283	64	2	graph	graph	NN
tedunderwood-com-8283	64	3	is	be	VBZ
tedunderwood-com-8283	64	4	based	base	VBN
tedunderwood-com-8283	64	5	on	on	IN
tedunderwood-com-8283	64	6	470,000	470,000	CD
tedunderwood-com-8283	64	7	volumes	volume	NNS
tedunderwood-com-8283	64	8	from	from	IN
tedunderwood-com-8283	64	9	HathiTrust	HathiTrust	NNP
tedunderwood-com-8283	64	10	1700	1700	CD
tedunderwood-com-8283	64	11	-	-	SYM
tedunderwood-com-8283	64	12	1899	1899	CD
tedunderwood-com-8283	64	13	;	;	:
tedunderwood-com-8283	64	14	it	-PRON-	PRP
tedunderwood-com-8283	64	15	’s	’	VBZ
tedunderwood-com-8283	64	16	the	the	DT
tedunderwood-com-8283	64	17	majority	majority	NN
tedunderwood-com-8283	64	18	of	of	IN
tedunderwood-com-8283	64	19	English	English	NNP
tedunderwood-com-8283	64	20	non	non	JJ
tedunderwood-com-8283	64	21	-	-	JJ
tedunderwood-com-8283	64	22	serial	serial	JJ
tedunderwood-com-8283	64	23	volumes	volume	NNS
tedunderwood-com-8283	64	24	in	in	IN
tedunderwood-com-8283	64	25	that	that	DT
tedunderwood-com-8283	64	26	period	period	NN
tedunderwood-com-8283	64	27	.	.	.
tedunderwood-com-8283	65	1	(	(	-LRB-
tedunderwood-com-8283	65	2	Illinois	Illinois	NNP
tedunderwood-com-8283	65	3	has	have	VBZ
tedunderwood-com-8283	65	4	signed	sign	VBN
tedunderwood-com-8283	65	5	an	an	DT
tedunderwood-com-8283	65	6	agreement	agreement	NN
tedunderwood-com-8283	65	7	with	with	IN
tedunderwood-com-8283	65	8	HathiTrust	HathiTrust	NNP
tedunderwood-com-8283	65	9	,	,	,
tedunderwood-com-8283	65	10	which	which	WDT
tedunderwood-com-8283	65	11	gives	give	VBZ
tedunderwood-com-8283	65	12	me	-PRON-	PRP
tedunderwood-com-8283	65	13	access	access	NN
tedunderwood-com-8283	65	14	to	to	IN
tedunderwood-com-8283	65	15	public	public	JJ
tedunderwood-com-8283	65	16	-	-	HYPH
tedunderwood-com-8283	65	17	domain	domain	NN
tedunderwood-com-8283	65	18	works	work	NNS
tedunderwood-com-8283	65	19	for	for	IN
tedunderwood-com-8283	65	20	research	research	NN
tedunderwood-com-8283	65	21	purposes	purpose	NNS
tedunderwood-com-8283	65	22	.	.	.
tedunderwood-com-8283	65	23	)	)	-RRB-
tedunderwood-com-8283	66	1	So	so	RB
tedunderwood-com-8283	66	2	each	each	DT
tedunderwood-com-8283	66	3	data	data	NN
tedunderwood-com-8283	66	4	point	point	NN
tedunderwood-com-8283	66	5	is	be	VBZ
tedunderwood-com-8283	66	6	the	the	DT
tedunderwood-com-8283	66	7	average	average	JJ
tedunderwood-com-8283	66	8	percentage	percentage	NN
tedunderwood-com-8283	66	9	of	of	IN
tedunderwood-com-8283	66	10	tokens	token	NNS
tedunderwood-com-8283	66	11	recognized	recognize	VBN
tedunderwood-com-8283	66	12	as	as	IN
tedunderwood-com-8283	66	13	words	word	NNS
tedunderwood-com-8283	66	14	in	in	IN
tedunderwood-com-8283	66	15	a	a	DT
tedunderwood-com-8283	66	16	given	give	VBN
tedunderwood-com-8283	66	17	year	year	NN
tedunderwood-com-8283	66	18	.	.	.
tedunderwood-com-8283	67	1	It	-PRON-	PRP
tedunderwood-com-8283	67	2	’s	’	VBZ
tedunderwood-com-8283	67	3	a	a	DT
tedunderwood-com-8283	67	4	pretty	pretty	RB
tedunderwood-com-8283	67	5	big	big	JJ
tedunderwood-com-8283	67	6	corpus	corpus	NN
tedunderwood-com-8283	67	7	,	,	,
tedunderwood-com-8283	67	8	but	but	CC
tedunderwood-com-8283	67	9	I	-PRON-	PRP
tedunderwood-com-8283	67	10	have	have	VBP
tedunderwood-com-8283	67	11	n’t	not	RB
tedunderwood-com-8283	67	12	tried	try	VBN
tedunderwood-com-8283	67	13	to	to	TO
tedunderwood-com-8283	67	14	do	do	VB
tedunderwood-com-8283	67	15	a	a	DT
tedunderwood-com-8283	67	16	thorough	thorough	JJ
tedunderwood-com-8283	67	17	,	,	,
tedunderwood-com-8283	67	18	systematic	systematic	JJ
tedunderwood-com-8283	67	19	,	,	,
tedunderwood-com-8283	67	20	evaluation	evaluation	NN
tedunderwood-com-8283	67	21	of	of	IN
tedunderwood-com-8283	67	22	accuracy	accuracy	NN
tedunderwood-com-8283	67	23	yet	yet	RB
tedunderwood-com-8283	67	24	.	.	.
tedunderwood-com-8283	68	1	As	as	IN
tedunderwood-com-8283	68	2	you	-PRON-	PRP
tedunderwood-com-8283	68	3	rightly	rightly	RB
tedunderwood-com-8283	68	4	note	note	VBP
tedunderwood-com-8283	68	5	in	in	IN
tedunderwood-com-8283	68	6	your	-PRON-	PRP$
tedunderwood-com-8283	68	7	paper	paper	NN
tedunderwood-com-8283	68	8	,	,	,
tedunderwood-com-8283	68	9	evaluation	evaluation	NN
tedunderwood-com-8283	68	10	requires	require	VBZ
tedunderwood-com-8283	68	11	attention	attention	NN
tedunderwood-com-8283	68	12	to	to	IN
tedunderwood-com-8283	68	13	both	both	DT
tedunderwood-com-8283	68	14	“	"	``
tedunderwood-com-8283	68	15	recall	recall	NN
tedunderwood-com-8283	68	16	”	"	''
tedunderwood-com-8283	68	17	and	and	CC
tedunderwood-com-8283	68	18	“	"	``
tedunderwood-com-8283	68	19	precision	precision	NN
tedunderwood-com-8283	68	20	,	,	,
tedunderwood-com-8283	68	21	”	"	''
tedunderwood-com-8283	68	22	and	and	CC
tedunderwood-com-8283	68	23	I	-PRON-	PRP
tedunderwood-com-8283	68	24	’m	be	VBP
tedunderwood-com-8283	68	25	not	not	RB
tedunderwood-com-8283	68	26	attempting	attempt	VBG
tedunderwood-com-8283	68	27	that	that	DT
tedunderwood-com-8283	68	28	yet	yet	RB
tedunderwood-com-8283	68	29	.	.	.
tedunderwood-com-8283	69	1	The	the	DT
tedunderwood-com-8283	69	2	graph	graph	NN
tedunderwood-com-8283	69	3	above	above	RB
tedunderwood-com-8283	69	4	is	be	VBZ
tedunderwood-com-8283	69	5	just	just	RB
tedunderwood-com-8283	69	6	“	"	``
tedunderwood-com-8283	69	7	the	the	DT
tedunderwood-com-8283	69	8	number	number	NN
tedunderwood-com-8283	69	9	of	of	IN
tedunderwood-com-8283	69	10	tokens	token	NNS
tedunderwood-com-8283	69	11	recognized	recognize	VBN
tedunderwood-com-8283	69	12	as	as	IN
tedunderwood-com-8283	69	13	words	word	NNS
tedunderwood-com-8283	69	14	,	,	,
tedunderwood-com-8283	69	15	”	"	''
tedunderwood-com-8283	69	16	and	and	CC
tedunderwood-com-8283	69	17	you	-PRON-	PRP
tedunderwood-com-8283	69	18	’re	be	VBZ
tedunderwood-com-8283	69	19	absolutely	absolutely	RB
tedunderwood-com-8283	69	20	right	right	JJ
tedunderwood-com-8283	69	21	that	that	IN
tedunderwood-com-8283	69	22	this	this	DT
tedunderwood-com-8283	69	23	figure	figure	NN
tedunderwood-com-8283	69	24	will	will	MD
tedunderwood-com-8283	69	25	depend	depend	VB
tedunderwood-com-8283	69	26	on	on	IN
tedunderwood-com-8283	69	27	dictionary	dictionary	JJ
tedunderwood-com-8283	69	28	coverage	coverage	NN
tedunderwood-com-8283	69	29	.	.	.
tedunderwood-com-8283	70	1	I	-PRON-	PRP
tedunderwood-com-8283	70	2	use	use	VBP
tedunderwood-com-8283	70	3	a	a	DT
tedunderwood-com-8283	70	4	multi	multi	JJ
tedunderwood-com-8283	70	5	-	-	JJ
tedunderwood-com-8283	70	6	lingual	lingual	JJ
tedunderwood-com-8283	70	7	dictionary	dictionary	JJ
tedunderwood-com-8283	70	8	,	,	,
tedunderwood-com-8283	70	9	but	but	CC
tedunderwood-com-8283	70	10	no	no	DT
tedunderwood-com-8283	70	11	dictionary	dictionary	NN
tedunderwood-com-8283	70	12	includes	include	VBZ
tedunderwood-com-8283	70	13	all	all	DT
tedunderwood-com-8283	70	14	possible	possible	JJ
tedunderwood-com-8283	70	15	languages	language	NNS
tedunderwood-com-8283	70	16	,	,	,
tedunderwood-com-8283	70	17	all	all	DT
tedunderwood-com-8283	70	18	possible	possible	JJ
tedunderwood-com-8283	70	19	proper	proper	JJ
tedunderwood-com-8283	70	20	nouns	noun	NNS
tedunderwood-com-8283	70	21	,	,	,
tedunderwood-com-8283	70	22	etc	etc	FW
tedunderwood-com-8283	70	23	.	.	.
tedunderwood-com-8283	71	1	Moreover	moreover	RB
tedunderwood-com-8283	71	2	,	,	,
tedunderwood-com-8283	71	3	by	by	IN
tedunderwood-com-8283	71	4	its	-PRON-	PRP$
tedunderwood-com-8283	71	5	very	very	JJ
tedunderwood-com-8283	71	6	nature	nature	NN
tedunderwood-com-8283	71	7	,	,	,
tedunderwood-com-8283	71	8	this	this	DT
tedunderwood-com-8283	71	9	is	be	VBZ
tedunderwood-com-8283	71	10	n’t	not	RB
tedunderwood-com-8283	71	11	a	a	DT
tedunderwood-com-8283	71	12	metric	metric	NN
tedunderwood-com-8283	71	13	that	that	WDT
tedunderwood-com-8283	71	14	can	can	MD
tedunderwood-com-8283	71	15	be	be	VB
tedunderwood-com-8283	71	16	used	use	VBN
tedunderwood-com-8283	71	17	to	to	TO
tedunderwood-com-8283	71	18	evaluate	evaluate	VB
tedunderwood-com-8283	71	19	contextual	contextual	JJ
tedunderwood-com-8283	71	20	spellchecking	spellchecking	NN
tedunderwood-com-8283	71	21	of	of	IN
tedunderwood-com-8283	71	22	pairs	pair	NNS
tedunderwood-com-8283	71	23	like	like	IN
tedunderwood-com-8283	71	24	“	"	``
tedunderwood-com-8283	71	25	fame	fame	NNP
tedunderwood-com-8283	71	26	/	/	SYM
tedunderwood-com-8283	71	27	same	same	JJ
tedunderwood-com-8283	71	28	.	.	.
tedunderwood-com-8283	71	29	”	"	''
tedunderwood-com-8283	71	30	To	to	TO
tedunderwood-com-8283	71	31	evaluate	evaluate	VB
tedunderwood-com-8283	71	32	that	that	DT
tedunderwood-com-8283	71	33	part	part	NN
tedunderwood-com-8283	71	34	of	of	IN
tedunderwood-com-8283	71	35	the	the	DT
tedunderwood-com-8283	71	36	workflow	workflow	NN
tedunderwood-com-8283	71	37	,	,	,
tedunderwood-com-8283	71	38	you	-PRON-	PRP
tedunderwood-com-8283	71	39	’re	be	VBZ
tedunderwood-com-8283	71	40	right	right	JJ
tedunderwood-com-8283	71	41	,	,	,
tedunderwood-com-8283	71	42	I	-PRON-	PRP
tedunderwood-com-8283	71	43	would	would	MD
tedunderwood-com-8283	71	44	need	need	VB
tedunderwood-com-8283	71	45	to	to	TO
tedunderwood-com-8283	71	46	use	use	VB
tedunderwood-com-8283	71	47	manually	manually	RB
tedunderwood-com-8283	71	48	-	-	HYPH
tedunderwood-com-8283	71	49	entered	enter	VBN
tedunderwood-com-8283	71	50	ground	ground	NN
tedunderwood-com-8283	71	51	truth	truth	NN
tedunderwood-com-8283	71	52	(	(	-LRB-
tedunderwood-com-8283	71	53	e.g.	e.g.	RB
tedunderwood-com-8283	72	1	the	the	DT
tedunderwood-com-8283	72	2	TCP	TCP	NNP
tedunderwood-com-8283	72	3	-	-	HYPH
tedunderwood-com-8283	72	4	ECCO	ECCO	NNP
tedunderwood-com-8283	72	5	corpus	corpus	NN
tedunderwood-com-8283	72	6	.	.	.
tedunderwood-com-8283	72	7	)	)	-RRB-
tedunderwood-com-8283	73	1	In	in	IN
tedunderwood-com-8283	73	2	short	short	JJ
tedunderwood-com-8283	73	3	,	,	,
tedunderwood-com-8283	73	4	I	-PRON-	PRP
tedunderwood-com-8283	73	5	’m	be	VBP
tedunderwood-com-8283	73	6	not	not	RB
tedunderwood-com-8283	73	7	making	make	VBG
tedunderwood-com-8283	73	8	strong	strong	JJ
tedunderwood-com-8283	73	9	claims	claim	NNS
tedunderwood-com-8283	73	10	about	about	IN
tedunderwood-com-8283	73	11	accuracy	accuracy	NN
tedunderwood-com-8283	73	12	here	here	RB
tedunderwood-com-8283	73	13	.	.	.
tedunderwood-com-8283	74	1	The	the	DT
tedunderwood-com-8283	74	2	word	word	NN
tedunderwood-com-8283	74	3	“	"	``
tedunderwood-com-8283	74	4	half	half	JJ
tedunderwood-com-8283	74	5	-	-	HYPH
tedunderwood-com-8283	74	6	decent	decent	JJ
tedunderwood-com-8283	74	7	”	"	''
tedunderwood-com-8283	74	8	in	in	IN
tedunderwood-com-8283	74	9	the	the	DT
tedunderwood-com-8283	74	10	title	title	NN
tedunderwood-com-8283	74	11	is	be	VBZ
tedunderwood-com-8283	74	12	very	very	RB
tedunderwood-com-8283	74	13	deliberately	deliberately	RB
tedunderwood-com-8283	74	14	chosen	choose	VBN
tedunderwood-com-8283	74	15	.	.	.
tedunderwood-com-8283	75	1	This	this	DT
tedunderwood-com-8283	75	2	is	be	VBZ
tedunderwood-com-8283	75	3	not	not	RB
tedunderwood-com-8283	75	4	a	a	DT
tedunderwood-com-8283	75	5	publication	publication	NN
tedunderwood-com-8283	75	6	:	:	:
tedunderwood-com-8283	75	7	it	-PRON-	PRP
tedunderwood-com-8283	75	8	’s	’	VBZ
tedunderwood-com-8283	75	9	a	a	DT
tedunderwood-com-8283	75	10	patch	patch	NN
tedunderwood-com-8283	75	11	that	that	WDT
tedunderwood-com-8283	75	12	I	-PRON-	PRP
tedunderwood-com-8283	75	13	’ve	have	VB
tedunderwood-com-8283	75	14	created	create	VBN
tedunderwood-com-8283	75	15	,	,	,
tedunderwood-com-8283	75	16	largely	largely	RB
tedunderwood-com-8283	75	17	on	on	IN
tedunderwood-com-8283	75	18	my	-PRON-	PRP$
tedunderwood-com-8283	75	19	own	own	JJ
tedunderwood-com-8283	75	20	time	time	NN
tedunderwood-com-8283	75	21	,	,	,
tedunderwood-com-8283	75	22	because	because	IN
tedunderwood-com-8283	75	23	I	-PRON-	PRP
tedunderwood-com-8283	75	24	needed	need	VBD
tedunderwood-com-8283	75	25	*	*	NFP
tedunderwood-com-8283	75	26	some	some	DT
tedunderwood-com-8283	75	27	*	*	NFP
tedunderwood-com-8283	75	28	patch	patch	VBP
tedunderwood-com-8283	75	29	for	for	IN
tedunderwood-com-8283	75	30	this	this	DT
tedunderwood-com-8283	75	31	problem	problem	NN
tedunderwood-com-8283	75	32	.	.	.
tedunderwood-com-8283	76	1	In	in	IN
tedunderwood-com-8283	76	2	research	research	NN
tedunderwood-com-8283	76	3	on	on	IN
tedunderwood-com-8283	76	4	the	the	DT
tedunderwood-com-8283	76	5	corrected	correct	VBN
tedunderwood-com-8283	76	6	corpus	corpus	NN
tedunderwood-com-8283	76	7	,	,	,
tedunderwood-com-8283	76	8	I	-PRON-	PRP
tedunderwood-com-8283	76	9	have	have	VBP
tedunderwood-com-8283	76	10	found	find	VBN
tedunderwood-com-8283	76	11	in	in	IN
tedunderwood-com-8283	76	12	practice	practice	NN
tedunderwood-com-8283	76	13	that	that	IN
tedunderwood-com-8283	76	14	it	-PRON-	PRP
tedunderwood-com-8283	76	15	lacks	lack	VBZ
tedunderwood-com-8283	76	16	the	the	DT
tedunderwood-com-8283	76	17	large	large	JJ
tedunderwood-com-8283	76	18	obvious	obvious	JJ
tedunderwood-com-8283	76	19	distortions	distortion	NNS
tedunderwood-com-8283	76	20	that	that	WDT
tedunderwood-com-8283	76	21	previously	previously	RB
tedunderwood-com-8283	76	22	made	make	VBD
tedunderwood-com-8283	76	23	diachronic	diachronic	JJ
tedunderwood-com-8283	76	24	analysis	analysis	NN
tedunderwood-com-8283	76	25	impossible	impossible	JJ
tedunderwood-com-8283	76	26	.	.	.
tedunderwood-com-8283	77	1	But	but	CC
tedunderwood-com-8283	77	2	I	-PRON-	PRP
tedunderwood-com-8283	77	3	have	have	VBP
tedunderwood-com-8283	77	4	n’t	not	RB
tedunderwood-com-8283	77	5	made	make	VBN
tedunderwood-com-8283	77	6	an	an	DT
tedunderwood-com-8283	77	7	effort	effort	NN
tedunderwood-com-8283	77	8	to	to	TO
tedunderwood-com-8283	77	9	rigorously	rigorously	RB
tedunderwood-com-8283	77	10	quantify	quantify	VB
tedunderwood-com-8283	77	11	the	the	DT
tedunderwood-com-8283	77	12	level	level	NN
tedunderwood-com-8283	77	13	of	of	IN
tedunderwood-com-8283	77	14	error	error	NN
tedunderwood-com-8283	77	15	that	that	WDT
tedunderwood-com-8283	77	16	remains	remain	VBZ
tedunderwood-com-8283	77	17	.	.	.
tedunderwood-com-8283	78	1	I	-PRON-	PRP
tedunderwood-com-8283	78	2	think	think	VBP
tedunderwood-com-8283	78	3	some	some	DT
tedunderwood-com-8283	78	4	of	of	IN
tedunderwood-com-8283	78	5	the	the	DT
tedunderwood-com-8283	78	6	people	people	NNS
tedunderwood-com-8283	78	7	I	-PRON-	PRP
tedunderwood-com-8283	78	8	’m	be	VBP
tedunderwood-com-8283	78	9	collaborating	collaborate	VBG
tedunderwood-com-8283	78	10	with	with	IN
tedunderwood-com-8283	78	11	will	will	MD
tedunderwood-com-8283	78	12	produce	produce	VB
tedunderwood-com-8283	78	13	quantitative	quantitative	JJ
tedunderwood-com-8283	78	14	accuracy	accuracy	NN
tedunderwood-com-8283	78	15	metrics	metric	NNS
tedunderwood-com-8283	78	16	fairly	fairly	RB
tedunderwood-com-8283	78	17	soon	soon	RB
tedunderwood-com-8283	78	18	.	.	.
tedunderwood-com-8283	79	1	But	but	CC
tedunderwood-com-8283	79	2	for	for	IN
tedunderwood-com-8283	79	3	me	-PRON-	PRP
tedunderwood-com-8283	79	4	the	the	DT
tedunderwood-com-8283	79	5	key	key	NN
tedunderwood-com-8283	79	6	is	be	VBZ
tedunderwood-com-8283	79	7	this	this	DT
tedunderwood-com-8283	79	8	:	:	:
tedunderwood-com-8283	79	9	even	even	RB
tedunderwood-com-8283	79	10	if	if	IN
tedunderwood-com-8283	79	11	I	-PRON-	PRP
tedunderwood-com-8283	79	12	had	have	VBD
tedunderwood-com-8283	79	13	a	a	DT
tedunderwood-com-8283	79	14	figure	figure	NN
tedunderwood-com-8283	79	15	based	base	VBN
tedunderwood-com-8283	79	16	on	on	IN
tedunderwood-com-8283	79	17	ground	ground	NN
tedunderwood-com-8283	79	18	truth	truth	NN
tedunderwood-com-8283	79	19	(	(	-LRB-
tedunderwood-com-8283	79	20	e.g.	e.g.	RB
tedunderwood-com-8283	80	1	“	"	``
tedunderwood-com-8283	80	2	90	90	CD
tedunderwood-com-8283	80	3	%	%	NN
tedunderwood-com-8283	80	4	precision	precision	NN
tedunderwood-com-8283	80	5	”	"	''
tedunderwood-com-8283	80	6	)	)	-RRB-
tedunderwood-com-8283	80	7	,	,	,
tedunderwood-com-8283	80	8	it	-PRON-	PRP
tedunderwood-com-8283	80	9	would	would	MD
tedunderwood-com-8283	80	10	n’t	not	RB
tedunderwood-com-8283	80	11	tell	tell	VB
tedunderwood-com-8283	80	12	me	-PRON-	PRP
tedunderwood-com-8283	80	13	what	what	WP
tedunderwood-com-8283	80	14	I	-PRON-	PRP
tedunderwood-com-8283	80	15	actually	actually	RB
tedunderwood-com-8283	80	16	need	need	VBP
tedunderwood-com-8283	80	17	to	to	TO
tedunderwood-com-8283	80	18	know	know	VB
tedunderwood-com-8283	80	19	—	—	:
tedunderwood-com-8283	80	20	which	which	WDT
tedunderwood-com-8283	80	21	is	be	VBZ
tedunderwood-com-8283	80	22	whether	whether	IN
tedunderwood-com-8283	80	23	the	the	DT
tedunderwood-com-8283	80	24	errors	error	NNS
tedunderwood-com-8283	80	25	(	(	-LRB-
tedunderwood-com-8283	80	26	and	and	CC
tedunderwood-com-8283	80	27	accurate	accurate	JJ
tedunderwood-com-8283	80	28	variants	variant	NNS
tedunderwood-com-8283	80	29	)	)	-RRB-
tedunderwood-com-8283	80	30	that	that	WDT
tedunderwood-com-8283	80	31	remain	remain	VBP
tedunderwood-com-8283	80	32	are	be	VBP
tedunderwood-com-8283	80	33	distributed	distribute	VBN
tedunderwood-com-8283	80	34	in	in	IN
tedunderwood-com-8283	80	35	a	a	DT
tedunderwood-com-8283	80	36	way	way	NN
tedunderwood-com-8283	80	37	that	that	WDT
tedunderwood-com-8283	80	38	becomes	become	VBZ
tedunderwood-com-8283	80	39	problematic	problematic	JJ
tedunderwood-com-8283	80	40	for	for	IN
tedunderwood-com-8283	80	41	a	a	DT
tedunderwood-com-8283	80	42	particular	particular	JJ
tedunderwood-com-8283	80	43	historical	historical	JJ
tedunderwood-com-8283	80	44	problem	problem	NN
tedunderwood-com-8283	80	45	or	or	CC
tedunderwood-com-8283	80	46	kind	kind	RB
tedunderwood-com-8283	80	47	of	of	RB
tedunderwood-com-8283	80	48	algorithmic	algorithmic	JJ
tedunderwood-com-8283	80	49	analysis	analysis	NN
tedunderwood-com-8283	80	50	.	.	.
tedunderwood-com-8283	81	1	That	that	DT
tedunderwood-com-8283	81	2	question	question	NN
tedunderwood-com-8283	81	3	is	be	VBZ
tedunderwood-com-8283	81	4	the	the	DT
tedunderwood-com-8283	81	5	decisive	decisive	JJ
tedunderwood-com-8283	81	6	one	one	NN
tedunderwood-com-8283	81	7	for	for	IN
tedunderwood-com-8283	81	8	me	-PRON-	PRP
tedunderwood-com-8283	81	9	,	,	,
tedunderwood-com-8283	81	10	and	and	CC
tedunderwood-com-8283	81	11	it	-PRON-	PRP
tedunderwood-com-8283	81	12	’s	’	VBZ
tedunderwood-com-8283	81	13	still	still	RB
tedunderwood-com-8283	81	14	going	go	VBG
tedunderwood-com-8283	81	15	to	to	TO
tedunderwood-com-8283	81	16	require	require	VB
tedunderwood-com-8283	81	17	case	case	NN
tedunderwood-com-8283	81	18	-	-	HYPH
tedunderwood-com-8283	81	19	by	by	IN
tedunderwood-com-8283	81	20	-	-	HYPH
tedunderwood-com-8283	81	21	case	case	NN
tedunderwood-com-8283	81	22	attention	attention	NN
tedunderwood-com-8283	81	23	.	.	.
tedunderwood-com-8283	82	1	Reply	Reply	NNP
tedunderwood-com-8283	82	2	↓	↓	NNP
tedunderwood-com-8283	82	3	Beatrice	Beatrice	NNP
tedunderwood-com-8283	82	4	Alex	Alex	NNP
tedunderwood-com-8283	82	5	on	on	IN
tedunderwood-com-8283	82	6	January	January	NNP
tedunderwood-com-8283	82	7	16	16	CD
tedunderwood-com-8283	82	8	,	,	,
tedunderwood-com-8283	82	9	2014	2014	CD
tedunderwood-com-8283	82	10	at	at	IN
tedunderwood-com-8283	82	11	4:18	4:18	CD
tedunderwood-com-8283	82	12	am	am	NN
tedunderwood-com-8283	82	13	said	say	VBD
tedunderwood-com-8283	82	14	:	:	:
tedunderwood-com-8283	82	15	A	a	DT
tedunderwood-com-8283	82	16	great	great	JJ
tedunderwood-com-8283	82	17	blog	blog	NN
tedunderwood-com-8283	82	18	post	post	NN
tedunderwood-com-8283	82	19	and	and	CC
tedunderwood-com-8283	82	20	thanks	thank	NNS
tedunderwood-com-8283	82	21	for	for	IN
tedunderwood-com-8283	82	22	sharing	share	VBG
tedunderwood-com-8283	82	23	the	the	DT
tedunderwood-com-8283	82	24	code	code	NN
tedunderwood-com-8283	82	25	.	.	.
tedunderwood-com-8283	83	1	There	there	EX
tedunderwood-com-8283	83	2	is	be	VBZ
tedunderwood-com-8283	83	3	definitely	definitely	RB
tedunderwood-com-8283	83	4	a	a	DT
tedunderwood-com-8283	83	5	need	need	NN
tedunderwood-com-8283	83	6	for	for	IN
tedunderwood-com-8283	83	7	more	more	JJR
tedunderwood-com-8283	83	8	research	research	NN
tedunderwood-com-8283	83	9	on	on	IN
tedunderwood-com-8283	83	10	quantitative	quantitative	JJ
tedunderwood-com-8283	83	11	accuracy	accuracy	NN
tedunderwood-com-8283	83	12	metrics	metric	NNS
tedunderwood-com-8283	83	13	for	for	IN
tedunderwood-com-8283	83	14	OCRed	OCRed	NNP
tedunderwood-com-8283	83	15	text	text	NN
tedunderwood-com-8283	83	16	,	,	,
tedunderwood-com-8283	83	17	especially	especially	RB
tedunderwood-com-8283	83	18	when	when	WRB
tedunderwood-com-8283	83	19	it	-PRON-	PRP
tedunderwood-com-8283	83	20	comes	come	VBZ
tedunderwood-com-8283	83	21	to	to	IN
tedunderwood-com-8283	83	22	using	use	VBG
tedunderwood-com-8283	83	23	it	-PRON-	PRP
tedunderwood-com-8283	83	24	for	for	IN
tedunderwood-com-8283	83	25	any	any	DT
tedunderwood-com-8283	83	26	kind	kind	NN
tedunderwood-com-8283	83	27	of	of	IN
tedunderwood-com-8283	83	28	text	text	NN
tedunderwood-com-8283	83	29	processing	processing	NN
tedunderwood-com-8283	83	30	.	.	.
tedunderwood-com-8283	84	1	So	so	RB
tedunderwood-com-8283	84	2	I	-PRON-	PRP
tedunderwood-com-8283	84	3	’ll	will	MD
tedunderwood-com-8283	84	4	be	be	VB
tedunderwood-com-8283	84	5	looking	look	VBG
tedunderwood-com-8283	84	6	forward	forward	RB
tedunderwood-com-8283	84	7	to	to	TO
tedunderwood-com-8283	84	8	see	see	VB
tedunderwood-com-8283	84	9	more	more	JJR
tedunderwood-com-8283	84	10	work	work	NN
tedunderwood-com-8283	84	11	in	in	IN
tedunderwood-com-8283	84	12	this	this	DT
tedunderwood-com-8283	84	13	area	area	NN
tedunderwood-com-8283	84	14	.	.	.
tedunderwood-com-8283	85	1	In	in	IN
tedunderwood-com-8283	85	2	your	-PRON-	PRP$
tedunderwood-com-8283	85	3	comment	comment	NN
tedunderwood-com-8283	85	4	above	above	IN
tedunderwood-com-8283	85	5	you	-PRON-	PRP
tedunderwood-com-8283	85	6	mention	mention	VBP
tedunderwood-com-8283	85	7	that	that	IN
tedunderwood-com-8283	85	8	each	each	DT
tedunderwood-com-8283	85	9	data	data	NN
tedunderwood-com-8283	85	10	point	point	NN
tedunderwood-com-8283	85	11	represents	represent	VBZ
tedunderwood-com-8283	85	12	the	the	DT
tedunderwood-com-8283	85	13	average	average	JJ
tedunderwood-com-8283	85	14	percentage	percentage	NN
tedunderwood-com-8283	85	15	of	of	IN
tedunderwood-com-8283	85	16	tokens	token	NNS
tedunderwood-com-8283	85	17	recognised	recognise	VBN
tedunderwood-com-8283	85	18	as	as	IN
tedunderwood-com-8283	85	19	a	a	DT
tedunderwood-com-8283	85	20	word	word	NN
tedunderwood-com-8283	85	21	in	in	IN
tedunderwood-com-8283	85	22	a	a	DT
tedunderwood-com-8283	85	23	given	give	VBN
tedunderwood-com-8283	85	24	year	year	NN
tedunderwood-com-8283	85	25	.	.	.
tedunderwood-com-8283	86	1	You	-PRON-	PRP
tedunderwood-com-8283	86	2	might	may	MD
tedunderwood-com-8283	86	3	just	just	RB
tedunderwood-com-8283	86	4	have	have	VB
tedunderwood-com-8283	86	5	used	use	VBN
tedunderwood-com-8283	86	6	the	the	DT
tedunderwood-com-8283	86	7	wrong	wrong	JJ
tedunderwood-com-8283	86	8	expression	expression	NN
tedunderwood-com-8283	86	9	as	as	IN
tedunderwood-com-8283	86	10	you	-PRON-	PRP
tedunderwood-com-8283	86	11	ca	can	MD
tedunderwood-com-8283	86	12	n’t	not	RB
tedunderwood-com-8283	86	13	average	average	VB
tedunderwood-com-8283	86	14	percentage	percentage	NN
tedunderwood-com-8283	86	15	unless	unless	IN
tedunderwood-com-8283	86	16	the	the	DT
tedunderwood-com-8283	86	17	document	document	NN
tedunderwood-com-8283	86	18	lengths	length	NNS
tedunderwood-com-8283	86	19	are	be	VBP
tedunderwood-com-8283	86	20	the	the	DT
tedunderwood-com-8283	86	21	same	same	JJ
tedunderwood-com-8283	86	22	.	.	.
tedunderwood-com-8283	87	1	You	-PRON-	PRP
tedunderwood-com-8283	87	2	need	need	VBP
tedunderwood-com-8283	87	3	to	to	TO
tedunderwood-com-8283	87	4	compute	compute	VB
tedunderwood-com-8283	87	5	one	one	CD
tedunderwood-com-8283	87	6	percentage	percentage	NN
tedunderwood-com-8283	87	7	of	of	IN
tedunderwood-com-8283	87	8	words	word	NNS
tedunderwood-com-8283	87	9	found	find	VBN
tedunderwood-com-8283	87	10	in	in	IN
tedunderwood-com-8283	87	11	the	the	DT
tedunderwood-com-8283	87	12	dictionary	dictionary	NN
tedunderwood-com-8283	87	13	for	for	IN
tedunderwood-com-8283	87	14	all	all	DT
tedunderwood-com-8283	87	15	documents	document	NNS
tedunderwood-com-8283	87	16	in	in	IN
tedunderwood-com-8283	87	17	the	the	DT
tedunderwood-com-8283	87	18	same	same	JJ
tedunderwood-com-8283	87	19	year	year	NN
tedunderwood-com-8283	87	20	.	.	.
tedunderwood-com-8283	88	1	The	the	DT
tedunderwood-com-8283	88	2	reason	reason	NN
tedunderwood-com-8283	88	3	being	be	VBG
tedunderwood-com-8283	88	4	is	be	VBZ
tedunderwood-com-8283	88	5	that	that	IN
tedunderwood-com-8283	88	6	averaging	average	VBG
tedunderwood-com-8283	88	7	percentages	percentage	NNS
tedunderwood-com-8283	88	8	will	will	MD
tedunderwood-com-8283	88	9	skew	skew	VB
tedunderwood-com-8283	88	10	the	the	DT
tedunderwood-com-8283	88	11	results	result	NNS
tedunderwood-com-8283	88	12	if	if	IN
tedunderwood-com-8283	88	13	the	the	DT
tedunderwood-com-8283	88	14	length	length	NN
tedunderwood-com-8283	88	15	of	of	IN
tedunderwood-com-8283	88	16	documents	document	NNS
tedunderwood-com-8283	88	17	varies	vary	VBZ
tedunderwood-com-8283	88	18	much	much	RB
tedunderwood-com-8283	88	19	across	across	IN
tedunderwood-com-8283	88	20	years	year	NNS
tedunderwood-com-8283	88	21	.	.	.
tedunderwood-com-8283	89	1	For	for	IN
tedunderwood-com-8283	89	2	example	example	NN
tedunderwood-com-8283	89	3	,	,	,
tedunderwood-com-8283	89	4	if	if	IN
tedunderwood-com-8283	89	5	you	-PRON-	PRP
tedunderwood-com-8283	89	6	have	have	VBP
tedunderwood-com-8283	89	7	three	three	CD
tedunderwood-com-8283	89	8	documents	document	NNS
tedunderwood-com-8283	89	9	for	for	IN
tedunderwood-com-8283	89	10	year	year	NN
tedunderwood-com-8283	89	11	1	1	CD
tedunderwood-com-8283	89	12	:	:	:
tedunderwood-com-8283	89	13	with	with	IN
tedunderwood-com-8283	89	14	50/100	50/100	CD
tedunderwood-com-8283	89	15	,	,	,
tedunderwood-com-8283	89	16	300/600	300/600	NN
tedunderwood-com-8283	89	17	and	and	CC
tedunderwood-com-8283	89	18	500/1500	500/1500	CD
tedunderwood-com-8283	89	19	words	word	NNS
tedunderwood-com-8283	89	20	in	in	IN
tedunderwood-com-8283	89	21	the	the	DT
tedunderwood-com-8283	89	22	dictionary	dictionary	NN
tedunderwood-com-8283	89	23	.	.	.
tedunderwood-com-8283	90	1	The	the	DT
tedunderwood-com-8283	90	2	average	average	JJ
tedunderwood-com-8283	90	3	percentage	percentage	NN
tedunderwood-com-8283	90	4	would	would	MD
tedunderwood-com-8283	90	5	be	be	VB
tedunderwood-com-8283	90	6	44.4444444	44.4444444	CD
tedunderwood-com-8283	90	7	.	.	.
tedunderwood-com-8283	91	1	The	the	DT
tedunderwood-com-8283	91	2	percentage	percentage	NN
tedunderwood-com-8283	91	3	across	across	IN
tedunderwood-com-8283	91	4	all	all	DT
tedunderwood-com-8283	91	5	documents	document	NNS
tedunderwood-com-8283	91	6	is	be	VBZ
tedunderwood-com-8283	91	7	850/2200	850/2200	CD
tedunderwood-com-8283	91	8	*	*	NFP
tedunderwood-com-8283	91	9	100=38.6363636363636	100=38.6363636363636	CD
tedunderwood-com-8283	91	10	.	.	.
tedunderwood-com-8283	92	1	You	-PRON-	PRP
tedunderwood-com-8283	92	2	have	have	VBP
tedunderwood-com-8283	92	3	another	another	DT
tedunderwood-com-8283	92	4	three	three	CD
tedunderwood-com-8283	92	5	documents	document	NNS
tedunderwood-com-8283	92	6	for	for	IN
tedunderwood-com-8283	92	7	year	year	NN
tedunderwood-com-8283	92	8	2	2	CD
tedunderwood-com-8283	92	9	:	:	:
tedunderwood-com-8283	92	10	with	with	IN
tedunderwood-com-8283	92	11	400/800	400/800	NNP
tedunderwood-com-8283	92	12	,	,	,
tedunderwood-com-8283	92	13	600/1200	600/1200	CD
tedunderwood-com-8283	92	14	and	and	CC
tedunderwood-com-8283	92	15	500/1500	500/1500	CD
tedunderwood-com-8283	92	16	words	word	NNS
tedunderwood-com-8283	92	17	in	in	IN
tedunderwood-com-8283	92	18	the	the	DT
tedunderwood-com-8283	92	19	dictionary	dictionary	NN
tedunderwood-com-8283	92	20	.	.	.
tedunderwood-com-8283	93	1	The	the	DT
tedunderwood-com-8283	93	2	first	first	JJ
tedunderwood-com-8283	93	3	2	2	CD
tedunderwood-com-8283	93	4	documents	document	NNS
tedunderwood-com-8283	93	5	are	be	VBP
tedunderwood-com-8283	93	6	longer	long	JJR
tedunderwood-com-8283	93	7	but	but	CC
tedunderwood-com-8283	93	8	have	have	VBP
tedunderwood-com-8283	93	9	the	the	DT
tedunderwood-com-8283	93	10	same	same	JJ
tedunderwood-com-8283	93	11	percentage	percentage	NN
tedunderwood-com-8283	93	12	of	of	IN
tedunderwood-com-8283	93	13	words	word	NNS
tedunderwood-com-8283	93	14	in	in	IN
tedunderwood-com-8283	93	15	the	the	DT
tedunderwood-com-8283	93	16	dictionary	dictionary	NN
tedunderwood-com-8283	93	17	as	as	IN
tedunderwood-com-8283	93	18	the	the	DT
tedunderwood-com-8283	93	19	first	first	JJ
tedunderwood-com-8283	93	20	two	two	CD
tedunderwood-com-8283	93	21	documents	document	NNS
tedunderwood-com-8283	93	22	in	in	IN
tedunderwood-com-8283	93	23	year	year	NN
tedunderwood-com-8283	93	24	1	1	CD
tedunderwood-com-8283	93	25	.	.	.
tedunderwood-com-8283	94	1	The	the	DT
tedunderwood-com-8283	94	2	average	average	JJ
tedunderwood-com-8283	94	3	percentage	percentage	NN
tedunderwood-com-8283	94	4	is	be	VBZ
tedunderwood-com-8283	94	5	still	still	RB
tedunderwood-com-8283	94	6	44.4444444	44.4444444	CD
tedunderwood-com-8283	94	7	.	.	.
tedunderwood-com-8283	95	1	However	however	RB
tedunderwood-com-8283	95	2	,	,	,
tedunderwood-com-8283	95	3	the	the	DT
tedunderwood-com-8283	95	4	recall	recall	NN
tedunderwood-com-8283	95	5	percentage	percentage	NN
tedunderwood-com-8283	95	6	across	across	IN
tedunderwood-com-8283	95	7	all	all	DT
tedunderwood-com-8283	95	8	documents	document	NNS
tedunderwood-com-8283	95	9	is	be	VBZ
tedunderwood-com-8283	95	10	1500/3500	1500/3500	CD
tedunderwood-com-8283	95	11	*	*	SYM
tedunderwood-com-8283	95	12	100=42.8571428571429	100=42.8571428571429	CD
tedunderwood-com-8283	95	13	.	.	.
tedunderwood-com-8283	96	1	I	-PRON-	PRP
tedunderwood-com-8283	96	2	’d	’d	MD
tedunderwood-com-8283	96	3	also	also	RB
tedunderwood-com-8283	96	4	be	be	VB
tedunderwood-com-8283	96	5	really	really	RB
tedunderwood-com-8283	96	6	interested	interested	JJ
tedunderwood-com-8283	96	7	to	to	TO
tedunderwood-com-8283	96	8	know	know	VB
tedunderwood-com-8283	96	9	what	what	WP
tedunderwood-com-8283	96	10	’s	’	VBZ
tedunderwood-com-8283	96	11	going	go	VBG
tedunderwood-com-8283	96	12	on	on	RP
tedunderwood-com-8283	96	13	for	for	IN
tedunderwood-com-8283	96	14	the	the	DT
tedunderwood-com-8283	96	15	outliers	outlier	NNS
tedunderwood-com-8283	96	16	in	in	IN
tedunderwood-com-8283	96	17	your	-PRON-	PRP$
tedunderwood-com-8283	96	18	graph	graph	NN
tedunderwood-com-8283	96	19	.	.	.
tedunderwood-com-8283	97	1	Beatrice	Beatrice	NNP
tedunderwood-com-8283	97	2	Alex	Alex	NNP
tedunderwood-com-8283	97	3	School	School	NNP
tedunderwood-com-8283	97	4	of	of	IN
tedunderwood-com-8283	97	5	Informatics	Informatics	NNP
tedunderwood-com-8283	97	6	,	,	,
tedunderwood-com-8283	97	7	University	University	NNP
tedunderwood-com-8283	97	8	of	of	IN
tedunderwood-com-8283	97	9	Edinburgh	Edinburgh	NNP
tedunderwood-com-8283	97	10	Reply	Reply	NNP
tedunderwood-com-8283	97	11	↓	↓	NNP
tedunderwood-com-8283	97	12	tedunderwood	tedunderwood	NN
tedunderwood-com-8283	97	13	on	on	IN
tedunderwood-com-8283	97	14	January	January	NNP
tedunderwood-com-8283	97	15	18	18	CD
tedunderwood-com-8283	97	16	,	,	,
tedunderwood-com-8283	97	17	2014	2014	CD
tedunderwood-com-8283	97	18	at	at	IN
tedunderwood-com-8283	97	19	5:01	5:01	CD
tedunderwood-com-8283	97	20	am	am	NN
tedunderwood-com-8283	97	21	said	say	VBN
tedunderwood-com-8283	97	22	:	:	:
tedunderwood-com-8283	97	23	Yep	yep	NN
tedunderwood-com-8283	97	24	—	—	:
tedunderwood-com-8283	97	25	you	-PRON-	PRP
tedunderwood-com-8283	97	26	’re	be	VBZ
tedunderwood-com-8283	97	27	quite	quite	RB
tedunderwood-com-8283	97	28	correct	correct	JJ
tedunderwood-com-8283	97	29	that	that	IN
tedunderwood-com-8283	97	30	there	there	EX
tedunderwood-com-8283	97	31	’s	’	VBZ
tedunderwood-com-8283	97	32	a	a	DT
tedunderwood-com-8283	97	33	difference	difference	NN
tedunderwood-com-8283	97	34	.	.	.
tedunderwood-com-8283	98	1	The	the	DT
tedunderwood-com-8283	98	2	graph	graph	NN
tedunderwood-com-8283	98	3	above	above	RB
tedunderwood-com-8283	98	4	is	be	VBZ
tedunderwood-com-8283	98	5	based	base	VBN
tedunderwood-com-8283	98	6	on	on	IN
tedunderwood-com-8283	98	7	calculations	calculation	NNS
tedunderwood-com-8283	98	8	that	that	WDT
tedunderwood-com-8283	98	9	do	do	VBP
tedunderwood-com-8283	98	10	n’t	not	RB
tedunderwood-com-8283	98	11	weight	weight	VB
tedunderwood-com-8283	98	12	documents	document	NNS
tedunderwood-com-8283	98	13	by	by	IN
tedunderwood-com-8283	98	14	length	length	NN
tedunderwood-com-8283	98	15	;	;	:
tedunderwood-com-8283	98	16	for	for	IN
tedunderwood-com-8283	98	17	simplicity	simplicity	NN
tedunderwood-com-8283	98	18	’s	’s	POS
tedunderwood-com-8283	98	19	sake	sake	NN
tedunderwood-com-8283	98	20	,	,	,
tedunderwood-com-8283	98	21	I	-PRON-	PRP
tedunderwood-com-8283	98	22	’ve	have	VB
tedunderwood-com-8283	98	23	treated	treat	VBN
tedunderwood-com-8283	98	24	each	each	DT
tedunderwood-com-8283	98	25	document	document	NN
tedunderwood-com-8283	98	26	as	as	IN
tedunderwood-com-8283	98	27	an	an	DT
tedunderwood-com-8283	98	28	equivalent	equivalent	JJ
tedunderwood-com-8283	98	29	data	data	NN
tedunderwood-com-8283	98	30	point	point	NN
tedunderwood-com-8283	98	31	.	.	.
tedunderwood-com-8283	99	1	But	but	CC
tedunderwood-com-8283	99	2	I	-PRON-	PRP
tedunderwood-com-8283	99	3	’m	be	VBP
tedunderwood-com-8283	99	4	really	really	RB
tedunderwood-com-8283	99	5	not	not	RB
tedunderwood-com-8283	99	6	aiming	aim	VBG
tedunderwood-com-8283	99	7	to	to	TO
tedunderwood-com-8283	99	8	evaluate	evaluate	VB
tedunderwood-com-8283	99	9	accuracy	accuracy	NN
tedunderwood-com-8283	99	10	with	with	IN
tedunderwood-com-8283	99	11	any	any	DT
tedunderwood-com-8283	99	12	finesse	finesse	NN
tedunderwood-com-8283	99	13	here	here	RB
tedunderwood-com-8283	99	14	:	:	:
tedunderwood-com-8283	99	15	the	the	DT
tedunderwood-com-8283	99	16	point	point	NN
tedunderwood-com-8283	99	17	of	of	IN
tedunderwood-com-8283	99	18	the	the	DT
tedunderwood-com-8283	99	19	illustration	illustration	NN
tedunderwood-com-8283	99	20	is	be	VBZ
tedunderwood-com-8283	99	21	purely	purely	RB
tedunderwood-com-8283	99	22	to	to	TO
tedunderwood-com-8283	99	23	show	show	VB
tedunderwood-com-8283	99	24	the	the	DT
tedunderwood-com-8283	99	25	gross	gross	JJ
tedunderwood-com-8283	99	26	difference	difference	NN
tedunderwood-com-8283	99	27	between	between	IN
tedunderwood-com-8283	99	28	the	the	DT
tedunderwood-com-8283	99	29	way	way	NN
tedunderwood-com-8283	99	30	correction	correction	NN
tedunderwood-com-8283	99	31	works	work	VBZ
tedunderwood-com-8283	99	32	in	in	IN
tedunderwood-com-8283	99	33	the	the	DT
tedunderwood-com-8283	99	34	18th	18th	JJ
tedunderwood-com-8283	99	35	century	century	NN
tedunderwood-com-8283	99	36	and	and	CC
tedunderwood-com-8283	99	37	the	the	DT
tedunderwood-com-8283	99	38	way	way	NN
tedunderwood-com-8283	99	39	it	-PRON-	PRP
tedunderwood-com-8283	99	40	works	work	VBZ
tedunderwood-com-8283	99	41	in	in	IN
tedunderwood-com-8283	99	42	the	the	DT
tedunderwood-com-8283	99	43	19th	19th	JJ
tedunderwood-com-8283	99	44	century	century	NN
tedunderwood-com-8283	99	45	.	.	.
tedunderwood-com-8283	100	1	The	the	DT
tedunderwood-com-8283	100	2	end	end	NN
tedunderwood-com-8283	100	3	of	of	IN
tedunderwood-com-8283	100	4	“	"	``
tedunderwood-com-8283	100	5	long	long	JJ
tedunderwood-com-8283	100	6	s	s	NNPS
tedunderwood-com-8283	100	7	”	"	''
tedunderwood-com-8283	100	8	is	be	VBZ
tedunderwood-com-8283	100	9	a	a	DT
tedunderwood-com-8283	100	10	very	very	RB
tedunderwood-com-8283	100	11	significant	significant	JJ
tedunderwood-com-8283	100	12	change	change	NN
tedunderwood-com-8283	100	13	that	that	WDT
tedunderwood-com-8283	100	14	dwarfs	dwarf	VBZ
tedunderwood-com-8283	100	15	a	a	DT
tedunderwood-com-8283	100	16	lot	lot	NN
tedunderwood-com-8283	100	17	of	of	IN
tedunderwood-com-8283	100	18	subtler	subtler	NNP
tedunderwood-com-8283	100	19	issues	issue	NNS
tedunderwood-com-8283	100	20	—	—	:
tedunderwood-com-8283	100	21	that	that	DT
tedunderwood-com-8283	100	22	’s	’	VBZ
tedunderwood-com-8283	100	23	all	all	PDT
tedunderwood-com-8283	100	24	the	the	DT
tedunderwood-com-8283	100	25	illustration	illustration	NN
tedunderwood-com-8283	100	26	is	be	VBZ
tedunderwood-com-8283	100	27	meant	mean	VBN
tedunderwood-com-8283	100	28	to	to	TO
tedunderwood-com-8283	100	29	reveal	reveal	VB
tedunderwood-com-8283	100	30	.	.	.
tedunderwood-com-8283	101	1	Reply	Reply	NNP
tedunderwood-com-8283	101	2	↓	↓	NNP
tedunderwood-com-8283	101	3	Pingback	Pingback	NNP
tedunderwood-com-8283	101	4	:	:	:
tedunderwood-com-8283	101	5	Possibly	possibly	RB
tedunderwood-com-8283	101	6	helpful	helpful	JJ
tedunderwood-com-8283	101	7	for	for	IN
tedunderwood-com-8283	101	8	cleaning	clean	VBG
tedunderwood-com-8283	101	9	18th	18th	JJ
tedunderwood-com-8283	101	10	C	C	NNP
tedunderwood-com-8283	101	11	OCR	OCR	NNP
tedunderwood-com-8283	101	12	,	,	,
tedunderwood-com-8283	101	13	@ihoffman	@ihoffman	NNP
tedunderwood-com-8283	101	14	.	.	.
tedunderwood-com-8283	102	1	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-texts-after-1700/	https://tedunderwood.com/2013/12/10/a-half-decent-ocr-normalizer-for-english-texts-after-1700/	``
tedunderwood-com-8283	102	2	John	John	NNP
tedunderwood-com-8283	102	3	Levin	Levin	NNP
tedunderwood-com-8283	102	4	(	(	-LRB-
tedunderwood-com-8283	102	5	@anterotesis	@anterotesis	NN
tedunderwood-com-8283	102	6	)	)	-RRB-
tedunderwood-com-8283	102	7	on	on	IN
tedunderwood-com-8283	102	8	June	June	NNP
tedunderwood-com-8283	102	9	30	30	CD
tedunderwood-com-8283	102	10	,	,	,
tedunderwood-com-8283	102	11	2015	2015	CD
tedunderwood-com-8283	102	12	at	at	IN
tedunderwood-com-8283	102	13	9:07	9:07	CD
tedunderwood-com-8283	102	14	am	am	NN
tedunderwood-com-8283	102	15	said	say	VBN
tedunderwood-com-8283	102	16	:	:	:
tedunderwood-com-8283	102	17	Are	be	VBP
tedunderwood-com-8283	102	18	you	-PRON-	PRP
tedunderwood-com-8283	102	19	still	still	RB
tedunderwood-com-8283	102	20	maintaining	maintain	VBG
tedunderwood-com-8283	102	21	this	this	DT
tedunderwood-com-8283	102	22	?	?	.
tedunderwood-com-8283	103	1	Have	have	VBP
tedunderwood-com-8283	103	2	just	just	RB
tedunderwood-com-8283	103	3	started	start	VBN
tedunderwood-com-8283	103	4	using	use	VBG
tedunderwood-com-8283	103	5	it	-PRON-	PRP
tedunderwood-com-8283	103	6	and	and	CC
tedunderwood-com-8283	103	7	found	find	VBD
tedunderwood-com-8283	103	8	a	a	DT
tedunderwood-com-8283	103	9	couple	couple	NN
tedunderwood-com-8283	103	10	of	of	IN
tedunderwood-com-8283	103	11	bugs	bug	NNS
tedunderwood-com-8283	103	12	.	.	.
tedunderwood-com-8283	104	1	John	John	NNP
tedunderwood-com-8283	104	2	Reply	Reply	NNP
tedunderwood-com-8283	104	3	↓	↓	NNP
tedunderwood-com-8283	104	4	Pingback	Pingback	NNP
tedunderwood-com-8283	104	5	:	:	:
tedunderwood-com-8283	104	6	OCR	OCR	NNP
tedunderwood-com-8283	104	7	Correction	Correction	NNP
tedunderwood-com-8283	104	8	script	script	NN
tedunderwood-com-8283	104	9	Leave	leave	VB
tedunderwood-com-8283	104	10	a	a	DT
tedunderwood-com-8283	104	11	Reply	Reply	NNP
tedunderwood-com-8283	104	12	Cancel	Cancel	NNP
tedunderwood-com-8283	104	13	reply	reply	NN
tedunderwood-com-8283	104	14	Enter	enter	VB
tedunderwood-com-8283	104	15	your	-PRON-	PRP$
tedunderwood-com-8283	104	16	comment	comment	NN
tedunderwood-com-8283	104	17	here	here	RB
tedunderwood-com-8283	104	18	...	...	.
tedunderwood-com-8283	105	1	Fill	fill	VB
tedunderwood-com-8283	105	2	in	in	IN
tedunderwood-com-8283	105	3	your	-PRON-	PRP$
tedunderwood-com-8283	105	4	details	detail	NNS
tedunderwood-com-8283	105	5	below	below	RB
tedunderwood-com-8283	105	6	or	or	CC
tedunderwood-com-8283	105	7	click	click	VB
tedunderwood-com-8283	105	8	an	an	DT
tedunderwood-com-8283	105	9	icon	icon	NN
tedunderwood-com-8283	105	10	to	to	TO
tedunderwood-com-8283	105	11	log	log	VB
tedunderwood-com-8283	105	12	in	in	RP
tedunderwood-com-8283	105	13	:	:	:
tedunderwood-com-8283	105	14	Email	Email	NNP
tedunderwood-com-8283	105	15	(	(	-LRB-
tedunderwood-com-8283	105	16	required	require	VBN
tedunderwood-com-8283	105	17	)	)	-RRB-
tedunderwood-com-8283	105	18	(	(	-LRB-
tedunderwood-com-8283	105	19	Address	address	NN
tedunderwood-com-8283	105	20	never	never	RB
tedunderwood-com-8283	105	21	made	make	VBD
tedunderwood-com-8283	105	22	public	public	JJ
tedunderwood-com-8283	105	23	)	)	-RRB-
tedunderwood-com-8283	105	24	Name	name	NN
tedunderwood-com-8283	105	25	(	(	-LRB-
tedunderwood-com-8283	105	26	required	require	VBN
tedunderwood-com-8283	105	27	)	)	-RRB-
tedunderwood-com-8283	105	28	Website	website	NN
tedunderwood-com-8283	105	29	You	-PRON-	PRP
tedunderwood-com-8283	105	30	are	be	VBP
tedunderwood-com-8283	105	31	commenting	comment	VBG
tedunderwood-com-8283	105	32	using	use	VBG
tedunderwood-com-8283	105	33	your	-PRON-	PRP$
tedunderwood-com-8283	105	34	WordPress.com	wordpress.com	CD
tedunderwood-com-8283	105	35	account	account	NN
tedunderwood-com-8283	105	36	.	.	.
tedunderwood-com-8283	106	1	(	(	-LRB-
tedunderwood-com-8283	106	2	 	  	_SP
tedunderwood-com-8283	106	3	Log	log	VB
tedunderwood-com-8283	106	4	 	  	_SP
tedunderwood-com-8283	106	5	Out	out	RB
tedunderwood-com-8283	106	6	 	  	_SP
tedunderwood-com-8283	106	7	/	/	,
tedunderwood-com-8283	106	8	  	  	_SP
tedunderwood-com-8283	106	9	Change	Change	NNP
tedunderwood-com-8283	106	10	 	  	_SP
tedunderwood-com-8283	106	11	)	)	-RRB-
tedunderwood-com-8283	106	12	You	-PRON-	PRP
tedunderwood-com-8283	106	13	are	be	VBP
tedunderwood-com-8283	106	14	commenting	comment	VBG
tedunderwood-com-8283	106	15	using	use	VBG
tedunderwood-com-8283	106	16	your	-PRON-	PRP$
tedunderwood-com-8283	106	17	Google	Google	NNP
tedunderwood-com-8283	106	18	account	account	NN
tedunderwood-com-8283	106	19	.	.	.
tedunderwood-com-8283	107	1	(	(	-LRB-
tedunderwood-com-8283	107	2	 	  	_SP
tedunderwood-com-8283	107	3	Log	log	VB
tedunderwood-com-8283	107	4	 	  	_SP
tedunderwood-com-8283	107	5	Out	out	RB
tedunderwood-com-8283	107	6	 	  	_SP
tedunderwood-com-8283	107	7	/	/	,
tedunderwood-com-8283	107	8	  	  	_SP
tedunderwood-com-8283	107	9	Change	Change	NNP
tedunderwood-com-8283	107	10	 	  	_SP
tedunderwood-com-8283	107	11	)	)	-RRB-
tedunderwood-com-8283	107	12	You	-PRON-	PRP
tedunderwood-com-8283	107	13	are	be	VBP
tedunderwood-com-8283	107	14	commenting	comment	VBG
tedunderwood-com-8283	107	15	using	use	VBG
tedunderwood-com-8283	107	16	your	-PRON-	PRP$
tedunderwood-com-8283	107	17	Twitter	Twitter	NNP
tedunderwood-com-8283	107	18	account	account	NN
tedunderwood-com-8283	107	19	.	.	.
tedunderwood-com-8283	108	1	(	(	-LRB-
tedunderwood-com-8283	108	2	 	  	_SP
tedunderwood-com-8283	108	3	Log	log	VB
tedunderwood-com-8283	108	4	 	  	_SP
tedunderwood-com-8283	108	5	Out	out	RB
tedunderwood-com-8283	108	6	 	  	_SP
tedunderwood-com-8283	108	7	/	/	,
tedunderwood-com-8283	108	8	  	  	_SP
tedunderwood-com-8283	108	9	Change	Change	NNP
tedunderwood-com-8283	108	10	 	  	_SP
tedunderwood-com-8283	108	11	)	)	-RRB-
tedunderwood-com-8283	108	12	You	-PRON-	PRP
tedunderwood-com-8283	108	13	are	be	VBP
tedunderwood-com-8283	108	14	commenting	comment	VBG
tedunderwood-com-8283	108	15	using	use	VBG
tedunderwood-com-8283	108	16	your	-PRON-	PRP$
tedunderwood-com-8283	108	17	Facebook	Facebook	NNP
tedunderwood-com-8283	108	18	account	account	NN
tedunderwood-com-8283	108	19	.	.	.
tedunderwood-com-8283	109	1	(	(	-LRB-
tedunderwood-com-8283	109	2	 	  	_SP
tedunderwood-com-8283	109	3	Log	log	VB
tedunderwood-com-8283	109	4	 	  	_SP
tedunderwood-com-8283	109	5	Out	out	RB
tedunderwood-com-8283	109	6	 	  	_SP
tedunderwood-com-8283	109	7	/	/	,
tedunderwood-com-8283	109	8	  	  	_SP
tedunderwood-com-8283	109	9	Change	Change	NNP
tedunderwood-com-8283	109	10	 	  	_SP
tedunderwood-com-8283	109	11	)	)	-RRB-
tedunderwood-com-8283	109	12	Cancel	Cancel	NNP
tedunderwood-com-8283	109	13	Connecting	Connecting	NNP
tedunderwood-com-8283	109	14	to	to	IN
tedunderwood-com-8283	109	15	%	%	NN
tedunderwood-com-8283	109	16	s	s	POS
tedunderwood-com-8283	109	17	Notify	notify	VB
tedunderwood-com-8283	109	18	me	-PRON-	PRP
tedunderwood-com-8283	109	19	of	of	IN
tedunderwood-com-8283	109	20	new	new	JJ
tedunderwood-com-8283	109	21	comments	comment	NNS
tedunderwood-com-8283	109	22	via	via	IN
tedunderwood-com-8283	109	23	email	email	NN
tedunderwood-com-8283	109	24	.	.	.
tedunderwood-com-8283	110	1	Notify	notify	VB
tedunderwood-com-8283	110	2	me	-PRON-	PRP
tedunderwood-com-8283	110	3	of	of	IN
tedunderwood-com-8283	110	4	new	new	JJ
tedunderwood-com-8283	110	5	posts	post	NNS
tedunderwood-com-8283	110	6	via	via	IN
tedunderwood-com-8283	110	7	email	email	NN
tedunderwood-com-8283	110	8	.	.	.
tedunderwood-com-8283	111	1	Blog	blog	VB
tedunderwood-com-8283	111	2	at	at	IN
tedunderwood-com-8283	111	3	WordPress.com	wordpress.com	CD
tedunderwood-com-8283	111	4	.	.	.
tedunderwood-com-8283	112	1	Post	post	VB
tedunderwood-com-8283	112	2	to	to	IN
tedunderwood-com-8283	112	3	Cancel	Cancel	NNP
tedunderwood-com-8283	112	4	%	%	NN
tedunderwood-com-8283	112	5	d	d	NN
tedunderwood-com-8283	112	6	bloggers	blogger	NNS
tedunderwood-com-8283	112	7	like	like	IN
tedunderwood-com-8283	112	8	this	this	DT
tedunderwood-com-8283	112	9	:	:	: