id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_ctayywu6gfdgbowc6nbcvpyjoe	Minh-Thang Luong	Parsing entire discourses as very long strings: Capturing topic continuity in grounded language learning	2013	12	.pdf	application/pdf	8049	1070	66	Parsing entire discourses as very long strings: Capturing topic continuity in context of language acquisition, this independence assumption discards cues that are important to the learner, e.g., the fact that consecutive utterances are likely to share the same Figure 1: Unigram Social Cue PCFGs (Johnson et al., 2012) – shown is a parse tree of the input utterance "wheres In addition, our discourse model produces a performance improvement in a language acquisition task mappings and inferring sentence topics as a grammar induction task where input strings are utterances key feature of these grammars is that parameter inference corresponds both to learning word-topic relations and learning the salience of social cues in utterances in a single parse, our proposed grammatical formalism is a bigram Markov process that models transitions among utterance topics. can use the ability of the Earley algorithm to compute prefix probabilities (Stolcke, 1995) to rescale Turning to the discourse models, social information and topic continuity both independently boost	./cache/work_ctayywu6gfdgbowc6nbcvpyjoe.pdf	./txt/work_ctayywu6gfdgbowc6nbcvpyjoe.txt