id	sid	tid	token	lemma	pos
j9601z42w7r	1	1	the	the	DET
j9601z42w7r	1	2	continued	continue	VERB
j9601z42w7r	1	3	exponential	exponential	ADJ
j9601z42w7r	1	4	growth	growth	NOUN
j9601z42w7r	1	5	of	of	ADP
j9601z42w7r	1	6	storage	storage	NOUN
j9601z42w7r	1	7	capacity	capacity	NOUN
j9601z42w7r	1	8	has	have	AUX
j9601z42w7r	1	9	catalyzed	catalyze	VERB
j9601z42w7r	1	10	the	the	DET
j9601z42w7r	1	11	broad	broad	ADJ
j9601z42w7r	1	12	acquisition	acquisition	NOUN
j9601z42w7r	1	13	of	of	ADP
j9601z42w7r	1	14	scientific	scientific	ADJ
j9601z42w7r	1	15	data	datum	NOUN
j9601z42w7r	1	16	which	which	PRON
j9601z42w7r	1	17	must	must	AUX
j9601z42w7r	1	18	be	be	AUX
j9601z42w7r	1	19	processed	process	VERB
j9601z42w7r	1	20	.	.	PUNCT
j9601z42w7r	2	1	while	while	SCONJ
j9601z42w7r	2	2	today	today	NOUN
j9601z42w7r	2	3	's	's	PART
j9601z42w7r	2	4	large	large	ADJ
j9601z42w7r	2	5	data	datum	NOUN
j9601z42w7r	2	6	analysis	analysis	NOUN
j9601z42w7r	2	7	systems	system	NOUN
j9601z42w7r	2	8	are	be	AUX
j9601z42w7r	2	9	highly	highly	ADV
j9601z42w7r	2	10	effective	effective	ADJ
j9601z42w7r	2	11	at	at	ADP
j9601z42w7r	2	12	establishing	establish	VERB
j9601z42w7r	2	13	data	datum	NOUN
j9601z42w7r	2	14	locality	locality	NOUN
j9601z42w7r	2	15	and	and	CCONJ
j9601z42w7r	2	16	eliminating	eliminate	VERB
j9601z42w7r	2	17	inter	inter	NOUN
j9601z42w7r	2	18	-	-	NOUN
j9601z42w7r	2	19	dependencies	dependency	NOUN
j9601z42w7r	2	20	,	,	PUNCT
j9601z42w7r	2	21	they	they	PRON
j9601z42w7r	2	22	are	be	AUX
j9601z42w7r	2	23	not	not	PART
j9601z42w7r	2	24	so	so	ADV
j9601z42w7r	2	25	easily	easily	ADV
j9601z42w7r	2	26	incorporated	incorporate	VERB
j9601z42w7r	2	27	into	into	ADP
j9601z42w7r	2	28	scientific	scientific	ADJ
j9601z42w7r	2	29	workflows	workflow	NOUN
j9601z42w7r	2	30	that	that	PRON
j9601z42w7r	2	31	are	be	AUX
j9601z42w7r	2	32	often	often	ADV
j9601z42w7r	2	33	complex	complex	ADJ
j9601z42w7r	2	34	and	and	CCONJ
j9601z42w7r	2	35	irregular	irregular	ADJ
j9601z42w7r	2	36	graphs	graph	NOUN
j9601z42w7r	2	37	of	of	ADP
j9601z42w7r	2	38	sequential	sequential	ADJ
j9601z42w7r	2	39	programs	program	NOUN
j9601z42w7r	2	40	with	with	ADP
j9601z42w7r	2	41	multiple	multiple	ADJ
j9601z42w7r	2	42	dependencies	dependency	NOUN
j9601z42w7r	2	43	.	.	PUNCT
j9601z42w7r	3	1	to	to	PART
j9601z42w7r	3	2	address	address	VERB
j9601z42w7r	3	3	the	the	DET
j9601z42w7r	3	4	needs	need	NOUN
j9601z42w7r	3	5	of	of	ADP
j9601z42w7r	3	6	scientific	scientific	ADJ
j9601z42w7r	3	7	computing	computing	NOUN
j9601z42w7r	3	8	,	,	PUNCT
j9601z42w7r	3	9	i	i	PRON
j9601z42w7r	3	10	propose	propose	VERB
j9601z42w7r	3	11	the	the	DET
j9601z42w7r	3	12	design	design	NOUN
j9601z42w7r	3	13	of	of	ADP
j9601z42w7r	3	14	an	an	DET
j9601z42w7r	3	15	active	active	ADJ
j9601z42w7r	3	16	storage	storage	NOUN
j9601z42w7r	3	17	cluster	cluster	NOUN
j9601z42w7r	3	18	file	file	NOUN
j9601z42w7r	3	19	system	system	NOUN
j9601z42w7r	3	20	which	which	PRON
j9601z42w7r	3	21	allows	allow	VERB
j9601z42w7r	3	22	for	for	ADP
j9601z42w7r	3	23	execution	execution	NOUN
j9601z42w7r	3	24	of	of	ADP
j9601z42w7r	3	25	regular	regular	ADJ
j9601z42w7r	3	26	unmodified	unmodified	ADJ
j9601z42w7r	3	27	applications	application	NOUN
j9601z42w7r	3	28	with	with	ADP
j9601z42w7r	3	29	full	full	ADJ
j9601z42w7r	3	30	data	datum	NOUN
j9601z42w7r	3	31	locality.this	locality.this	DET
j9601z42w7r	3	32	dissertation	dissertation	NOUN
j9601z42w7r	3	33	analyzes	analyze	VERB
j9601z42w7r	3	34	the	the	DET
j9601z42w7r	3	35	potential	potential	ADJ
j9601z42w7r	3	36	benefits	benefit	NOUN
j9601z42w7r	3	37	of	of	ADP
j9601z42w7r	3	38	exploiting	exploit	VERB
j9601z42w7r	3	39	the	the	DET
j9601z42w7r	3	40	structural	structural	ADJ
j9601z42w7r	3	41	information	information	NOUN
j9601z42w7r	3	42	already	already	ADV
j9601z42w7r	3	43	available	available	ADJ
j9601z42w7r	3	44	in	in	ADP
j9601z42w7r	3	45	scientific	scientific	ADJ
j9601z42w7r	3	46	workflows	workflow	NOUN
j9601z42w7r	3	47	-the	-the	DET
j9601z42w7r	3	48	explicit	explicit	ADJ
j9601z42w7r	3	49	dependencies	dependency	NOUN
j9601z42w7r	3	50	-to	-to	PUNCT
j9601z42w7r	3	51	achieve	achieve	VERB
j9601z42w7r	3	52	a	a	DET
j9601z42w7r	3	53	scalable	scalable	ADJ
j9601z42w7r	3	54	and	and	CCONJ
j9601z42w7r	3	55	stable	stable	ADJ
j9601z42w7r	3	56	system	system	NOUN
j9601z42w7r	3	57	.	.	PUNCT
j9601z42w7r	4	1	i	i	PRON
j9601z42w7r	4	2	begin	begin	VERB
j9601z42w7r	4	3	with	with	ADP
j9601z42w7r	4	4	an	an	DET
j9601z42w7r	4	5	outline	outline	NOUN
j9601z42w7r	4	6	of	of	ADP
j9601z42w7r	4	7	the	the	DET
j9601z42w7r	4	8	design	design	NOUN
j9601z42w7r	4	9	of	of	ADP
j9601z42w7r	4	10	the	the	DET
j9601z42w7r	4	11	confuga	confuga	ADJ
j9601z42w7r	4	12	active	active	ADJ
j9601z42w7r	4	13	storage	storage	NOUN
j9601z42w7r	4	14	cluster	cluster	NOUN
j9601z42w7r	4	15	file	file	NOUN
j9601z42w7r	4	16	system	system	NOUN
j9601z42w7r	4	17	and	and	CCONJ
j9601z42w7r	4	18	its	its	PRON
j9601z42w7r	4	19	applicability	applicability	NOUN
j9601z42w7r	4	20	to	to	ADP
j9601z42w7r	4	21	scientific	scientific	ADJ
j9601z42w7r	4	22	computing	computing	NOUN
j9601z42w7r	4	23	.	.	PUNCT
j9601z42w7r	5	1	the	the	DET
j9601z42w7r	5	2	remainder	remainder	NOUN
j9601z42w7r	5	3	of	of	ADP
j9601z42w7r	5	4	the	the	DET
j9601z42w7r	5	5	dissertation	dissertation	NOUN
j9601z42w7r	5	6	examines	examine	VERB
j9601z42w7r	5	7	the	the	DET
j9601z42w7r	5	8	techniques	technique	NOUN
j9601z42w7r	5	9	used	use	VERB
j9601z42w7r	5	10	to	to	PART
j9601z42w7r	5	11	achieve	achieve	VERB
j9601z42w7r	5	12	a	a	DET
j9601z42w7r	5	13	scalable	scalable	ADJ
j9601z42w7r	5	14	and	and	CCONJ
j9601z42w7r	5	15	stable	stable	ADJ
j9601z42w7r	5	16	system	system	NOUN
j9601z42w7r	5	17	.	.	PUNCT
j9601z42w7r	6	1	first	first	ADV
j9601z42w7r	6	2	,	,	PUNCT
j9601z42w7r	6	3	file	file	NOUN
j9601z42w7r	6	4	system	system	NOUN
j9601z42w7r	6	5	access	access	NOUN
j9601z42w7r	6	6	by	by	ADP
j9601z42w7r	6	7	jobs	job	NOUN
j9601z42w7r	6	8	is	be	AUX
j9601z42w7r	6	9	scoped	scope	VERB
j9601z42w7r	6	10	to	to	PART
j9601z42w7r	6	11	explicitly	explicitly	ADV
j9601z42w7r	6	12	defined	define	VERB
j9601z42w7r	6	13	dependencies	dependency	NOUN
j9601z42w7r	6	14	resolved	resolve	VERB
j9601z42w7r	6	15	at	at	ADP
j9601z42w7r	6	16	job	job	NOUN
j9601z42w7r	6	17	dispatch	dispatch	NOUN
j9601z42w7r	6	18	.	.	PUNCT
j9601z42w7r	7	1	second	second	ADJ
j9601z42w7r	7	2	,	,	PUNCT
j9601z42w7r	7	3	workflow	workflow	NOUN
j9601z42w7r	7	4	's	's	PART
j9601z42w7r	7	5	structural	structural	ADJ
j9601z42w7r	7	6	information	information	NOUN
j9601z42w7r	7	7	is	be	AUX
j9601z42w7r	7	8	harnessed	harness	VERB
j9601z42w7r	7	9	to	to	PART
j9601z42w7r	7	10	direct	direct	VERB
j9601z42w7r	7	11	and	and	CCONJ
j9601z42w7r	7	12	control	control	VERB
j9601z42w7r	7	13	necessary	necessary	ADJ
j9601z42w7r	7	14	file	file	NOUN
j9601z42w7r	7	15	transfers	transfer	NOUN
j9601z42w7r	7	16	to	to	PART
j9601z42w7r	7	17	enforce	enforce	VERB
j9601z42w7r	7	18	cluster	cluster	NOUN
j9601z42w7r	7	19	stability	stability	NOUN
j9601z42w7r	7	20	and	and	CCONJ
j9601z42w7r	7	21	maintain	maintain	VERB
j9601z42w7r	7	22	performance	performance	NOUN
j9601z42w7r	7	23	.	.	PUNCT
j9601z42w7r	8	1	third	third	ADJ
j9601z42w7r	8	2	,	,	PUNCT
j9601z42w7r	8	3	control	control	NOUN
j9601z42w7r	8	4	of	of	ADP
j9601z42w7r	8	5	transfers	transfer	NOUN
j9601z42w7r	8	6	is	be	AUX
j9601z42w7r	8	7	selectively	selectively	ADV
j9601z42w7r	8	8	relaxed	relaxed	ADJ
j9601z42w7r	8	9	to	to	PART
j9601z42w7r	8	10	improve	improve	VERB
j9601z42w7r	8	11	performance	performance	NOUN
j9601z42w7r	8	12	by	by	ADP
j9601z42w7r	8	13	limiting	limit	VERB
j9601z42w7r	8	14	any	any	DET
j9601z42w7r	8	15	negative	negative	ADJ
j9601z42w7r	8	16	effects	effect	NOUN
j9601z42w7r	8	17	of	of	ADP
j9601z42w7r	8	18	centralized	centralized	ADJ
j9601z42w7r	8	19	transfer	transfer	NOUN
j9601z42w7r	9	1	management.this	management.this	NOUN
j9601z42w7r	9	2	work	work	NOUN
j9601z42w7r	9	3	benefits	benefit	VERB
j9601z42w7r	9	4	users	user	NOUN
j9601z42w7r	9	5	by	by	ADP
j9601z42w7r	9	6	providing	provide	VERB
j9601z42w7r	9	7	a	a	DET
j9601z42w7r	9	8	complete	complete	ADJ
j9601z42w7r	9	9	batch	batch	NOUN
j9601z42w7r	9	10	execution	execution	NOUN
j9601z42w7r	9	11	platform	platform	NOUN
j9601z42w7r	9	12	joined	join	VERB
j9601z42w7r	9	13	with	with	ADP
j9601z42w7r	9	14	a	a	DET
j9601z42w7r	9	15	cluster	cluster	NOUN
j9601z42w7r	9	16	file	file	NOUN
j9601z42w7r	9	17	system	system	NOUN
j9601z42w7r	9	18	.	.	PUNCT
j9601z42w7r	10	1	the	the	DET
j9601z42w7r	10	2	user	user	NOUN
j9601z42w7r	10	3	does	do	AUX
j9601z42w7r	10	4	not	not	PART
j9601z42w7r	10	5	need	need	VERB
j9601z42w7r	10	6	to	to	PART
j9601z42w7r	10	7	redesign	redesign	VERB
j9601z42w7r	10	8	their	their	PRON
j9601z42w7r	10	9	workflow	workflow	NOUN
j9601z42w7r	10	10	or	or	CCONJ
j9601z42w7r	10	11	provide	provide	VERB
j9601z42w7r	10	12	additional	additional	ADJ
j9601z42w7r	10	13	consideration	consideration	NOUN
j9601z42w7r	10	14	to	to	ADP
j9601z42w7r	10	15	the	the	DET
j9601z42w7r	10	16	management	management	NOUN
j9601z42w7r	10	17	of	of	ADP
j9601z42w7r	10	18	data	datum	NOUN
j9601z42w7r	10	19	dependencies	dependency	NOUN
j9601z42w7r	10	20	.	.	PUNCT
j9601z42w7r	11	1	system	system	NOUN
j9601z42w7r	11	2	stability	stability	NOUN
j9601z42w7r	11	3	and	and	CCONJ
j9601z42w7r	11	4	performance	performance	NOUN
j9601z42w7r	11	5	is	be	AUX
j9601z42w7r	11	6	managed	manage	VERB
j9601z42w7r	11	7	by	by	ADP
j9601z42w7r	11	8	the	the	DET
j9601z42w7r	11	9	cluster	cluster	NOUN
j9601z42w7r	11	10	file	file	NOUN
j9601z42w7r	11	11	system	system	NOUN
j9601z42w7r	11	12	while	while	SCONJ
j9601z42w7r	11	13	providing	provide	VERB
j9601z42w7r	11	14	jobs	job	NOUN
j9601z42w7r	11	15	with	with	ADP
j9601z42w7r	11	16	complete	complete	ADJ
j9601z42w7r	11	17	data	data	NOUN
j9601z42w7r	11	18	locality	locality	NOUN
j9601z42w7r	11	19	.	.	PUNCT