Báo cáo khoa học: "Extracting and modeling durations for habits and events from Twitter" doc

Báo cáo khoa học: "Extracting and modeling durations for habits and events from Twitter" doc

Báo cáo khoa học: "Extracting and modeling durations for habits and events from Twitter" doc

... Association for Computational Linguistics, pages 223–227, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Extracting and modeling durations for habits and events ... automatically extracting information about typical durations for events from tweets posted to the Twitter microblogging site. Twitter is a rich resource for...
Ngày tải lên : 16/03/2014, 20:20
  • 5
  • 311
  • 0
Báo cáo khoa học: " a Movie Dialogue Corpus for Research and Development" potx

Báo cáo khoa học: " a Movie Dialogue Corpus for Research and Development" potx

... elements are extracted from the scripts: speakers, utterances and context. The utterance and speaker information elements contain what is said at each dialogue turn and the corresponding ... as: Happy Birthday Wanda June, Hannah and Her Sisters and All About Eve. In the lower-left corner of the figure we can find movies with few dia- logues and few turns, as for instanc...
Ngày tải lên : 07/03/2014, 18:20
  • 5
  • 424
  • 0
Báo cáo khoa học: Selectivity of pyruvate kinase for Na+ and K+ in water/dimethylsulfoxide mixtures docx

Báo cáo khoa học: Selectivity of pyruvate kinase for Na+ and K+ in water/dimethylsulfoxide mixtures docx

... K iapp for K + and Na + decreased 116 and 135-fold between 20 and 40% dimethylsulfoxide. The ratios of K iapp /K 0.5 app for K + and Na + were 34–3.5 and 3.3–0.2, respectively. There- fore, dimethylsulfoxide ... Mg 2+ ,theK i values for Na + and for Mg 2+ were 0.22 m M and 0.41 m M , respectively. In the competition of Mg 2+ with K + ,theK i for Mg 2+ was 4.38 m M . Th...
Ngày tải lên : 08/03/2014, 02:20
  • 9
  • 460
  • 0
Báo cáo khoa học: "Reduced n-gram models for English and Chinese corpora" ppt

Báo cáo khoa học: "Reduced n-gram models for English and Chinese corpora" ppt

... 14.6 for a 40-million-word corpus and 11.0 for a 500-million-word corpus while obtaining 5.8% and 4.2% improvements in perplexities. For Chinese, we gain a 16.9% perplexity reductions and ... Newspaper from 1991 to 1996 (125 million syllables); from the Xinhua News Agency from 1994 to 1996 (25 million syllables); and from transcripts of China Radio International...
Ngày tải lên : 23/03/2014, 18:20
  • 7
  • 273
  • 0
Báo cáo khoa học: "A Probabilistic Modeling Framework for Lexical Entailment" potx

Báo cáo khoa học: "A Probabilistic Modeling Framework for Lexical Entailment" potx

... Association for Computational Linguistics:shortpapers, pages 558–563, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics A Probabilistic Modeling Framework for Lexical ... of 558 entailment resources and the impact of rule chaining and multiple evidence on entailment likelihood. An additional observation from these and other systems is that t...
Ngày tải lên : 30/03/2014, 21:20
  • 6
  • 376
  • 0
Báo cáo khoa học: "LR RECURSIVE TRANSITION NETWORKS FOR EARLEY AND TOMITA PARSING" docx

Báo cáo khoa học: "LR RECURSIVE TRANSITION NETWORKS FOR EARLEY AND TOMITA PARSING" docx

... Figure 1. Expanding Rule#l: S ~NP VP. A. Expanding the nonterminal symbol S. B. Expanding the rule node for Rule #1. C. Expanding the symbol node VP. D. Expanding the symbol node NP. E, Expanding ... packed forest follows immediately from our merge option. His graph stack and his parse forest are, for us, the same entity: the shared parse tree. Even the LR table is seen to deriv...
Ngày tải lên : 31/03/2014, 06:20
  • 8
  • 313
  • 0
Báo cáo khoa học: "INTEGRATING MULTIPLE KNOWLEDGE SOURCES FOR DETECTION AND CORRECTION OF REPAIRS IN HUMAN-COMPUTER DIALOG*" potx

Báo cáo khoa học: "INTEGRATING MULTIPLE KNOWLEDGE SOURCES FOR DETECTION AND CORRECTION OF REPAIRS IN HUMAN-COMPUTER DIALOG*" potx

... disfluencies as to type and frequency, and are investigating methods for their automatic detection and correction. Here we re- port promising results on detection and correction of repairs ... in 62 out of 68 cases for syntax alone, and in 60 out of 64 cases using combined syntax and semantics. In both cases, a large number of sentences (29% for syntax, 50% for sem...
Ngày tải lên : 31/03/2014, 06:20
  • 8
  • 370
  • 0
Tài liệu Báo cáo khoa học: "Modified Distortion Matrices for Phrase-Based Statistical Machine Translation" doc

Tài liệu Báo cáo khoa học: "Modified Distortion Matrices for Phrase-Based Statistical Machine Translation" doc

... Riezler and John T. Maxwell. 2005. On some pitfalls in automatic evaluation and significance testing for MT. In Proceedings of the ACL Workshop on In- trinsic and Extrinsic Evaluation Measures for ... to in-decoding reordering, and therefore require an exhaustive reordering rule set. Two recent works (Bisazza and Federico, 2010; Andreas et al., 2011) opt instead for a hybrid wa...
Ngày tải lên : 19/02/2014, 19:20
  • 10
  • 473
  • 0
Tài liệu Báo cáo khoa học: "SenseLearner: Word Sense Disambiguation for All Words in Unrestricted Text" doc

Tài liệu Báo cáo khoa học: "SenseLearner: Word Sense Disambiguation for All Words in Unrestricted Text" doc

... com- mon sense reasoning, and others, require knowledge about word meanings, and word sense disambiguation is considered essential for all these applications. Most of the efforts in solving this ... classes, semantic density, and others. In recent SENSEVAL-3 evaluations, the most suc- cessful approaches for all words word sense disam- biguation relied on information drawn from ann...
Ngày tải lên : 20/02/2014, 15:20
  • 4
  • 399
  • 0
Tài liệu Báo cáo khoa học: "A Terminological Simplification Transformation for Natural Language Question-Answering Systems" doc

Tài liệu Báo cáo khoa học: "A Terminological Simplification Transformation for Natural Language Question-Answering Systems" doc

... PATIENTS TO DOCTORS OVER PHYS DOCID) OVER PATID DOCID) Note that while no table exists for physician SPECIALTIES, we can nonetheless give a rule for this predicate in way that is uniform with ... domain. This prepares the way for the simplification transformation itself, which will rely on a limited and sound form of inference to reverse the axiomatization and transform the...
Ngày tải lên : 21/02/2014, 20:20
  • 6
  • 299
  • 0
Từ khóa: