Báo cáo khoa học: "Using WordNet to Automatically Deduce Relations between Words in Noun-Noun Compounds" docx

Báo cáo khoa học: "Using WordNet to Automatically Deduce Relations between Words in Noun-Noun Compounds" docx

Báo cáo khoa học: "Using WordNet to Automatically Deduce Relations between Words in Noun-Noun Compounds" docx

... Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 160–167, Sydney, July 2006. c 2006 Association for Computational Linguistics Using WordNet to Automatically Deduce Relations ... disambiguat- ing noun-noun compounds by automatically de- ducing the correct semantic relationship between their constituent words. Our approach to compound disambiguation...

Ngày tải lên: 08/03/2014, 02:21

8 319 0
Báo cáo khoa học: "Using Syntax to Disambiguate Explicit Discourse Connectives in Text" pot

Báo cáo khoa học: "Using Syntax to Disambiguate Explicit Discourse Connectives in Text" pot

... hierarchy of senses. In our experiments we consider only the top level categories: Ex- pansion (one clause is elaborating information in the other), Comparison (information in the two clauses is ... articles: Self Category The highest node in the tree which dominates the words in the connective but nothing else. For single word connectives, this might correspond to the POS tag o...

Ngày tải lên: 08/03/2014, 01:20

4 441 0
Báo cáo khoa học: "Using Emoticons to reduce Dependency in Machine Learning Techniques for Sentiment Classification" pot

Báo cáo khoa học: "Using Emoticons to reduce Dependency in Machine Learning Techniques for Sentiment Classification" pot

... classification training data. 2,000 articles containing smiles and 2,000 articles containing frowns were held-out as optimising test data. We took increasing amounts of articles from the remaining dataset ... testing showed that the results are not signifi- cantly different when training on one topic and test- ing on another. It is interesting to note, though, that providing a dataset of mixe...

Ngày tải lên: 17/03/2014, 06:20

6 434 0
Báo cáo khoa học: "Using Readers to Identify Lexical Cohesive Structures in Texts" potx

Báo cáo khoa học: "Using Readers to Identify Lexical Cohesive Structures in Texts" potx

... annotators by taking the proportions of items marked as anchored by annotator in the whole of the dataset, and assuming that for every word, the person was toss- ing a coin with P(heads) = , independently ... validating them experimentally – may be applied to data resulting from other kinds of ex- ploratory experiments to gain insights about the phe- nomena at hand. Acknowledgment I wou...

Ngày tải lên: 17/03/2014, 06:20

6 378 0
Báo cáo khoa học: "USING CLASSIFICATION TO GENERATE TEXT" docx

Báo cáo khoa học: "USING CLASSIFICATION TO GENERATE TEXT" docx

... default-inheritance system that inherits properties from superclass to subclass, us- ing Touretsky's [1986] minimal inferential dis- tance principle to resolve conflicts; • various support tools, ... click- able buttons in the response window; objects to be added to the discourse in- focus list; and a testing function that determines if a query is answerable. Content-...

Ngày tải lên: 17/03/2014, 08:20

8 246 0
Báo cáo khoa học: "Using Focus to Generate Complex and Simple Sentences" pot

Báo cáo khoa học: "Using Focus to Generate Complex and Simple Sentences" pot

... containing a subordinate clause (sentence 2). The sentences in 1 and 2 also show that a generation system should be able to choose between definite and indefinite reference and decide when to ... system is able to recognize underlying semantic and rhetorical relations between propositions to combine phrases using textual connectives, also an important basis for combining...

Ngày tải lên: 17/03/2014, 19:21

8 349 1
Báo cáo khoa học: "Using Speech to Reply to SMS Messages While Driving: An In-Car Simulator User Study" docx

Báo cáo khoa học: "Using Speech to Reply to SMS Messages While Driving: An In-Car Simulator User Study" docx

... correct or incorrect in order to avoid priming users to pay more or less attention in subsequent messages. Users did not have to finish listening to the entire list before making their selection. ... ability to listen to incoming SMS messages using text -to- speech (TTS). Au- tomatic speech recognition (ASR) affords users a hands-free, eyes-free method of replying to S...

Ngày tải lên: 23/03/2014, 16:20

5 325 0
Báo cáo khoa học: "Using Rejuvenation to Improve Particle Filtering for Bayesian Word Segmentation" doc

Báo cáo khoa học: "Using Rejuvenation to Improve Particle Filtering for Bayesian Word Segmentation" doc

... idea is to restore sample diversity after each resampling step by per- forming MCMC resampling steps on each particle’s history, thus leading to particles with different his- tories in each generation, ... of the gap to be interesting in its own right, suggesting a general dif- ference in learning behaviour between batch and in- cremental learners, especially given the similar...

Ngày tải lên: 30/03/2014, 17:20

5 222 0
Báo cáo khoa học: "Using Crowdsourcing to Improve the Evaluation of Grammatical Error Detection Systems" pdf

Báo cáo khoa học: "Using Crowdsourcing to Improve the Evaluation of Grammatical Error Detection Systems" pdf

... Using Crowdsourcing to Improve the Evaluation of Grammatical Error Detection Systems Nitin Madnani a Joel Tetreault a Martin Chodorow b Alla Rozovskaya c a Educational Testing Service Princeton, ... promise. 508 ing to both address the lack of appropriate evaluation metrics and to make system comparison easier. Our solution is general enough for, in the simplest case, intrinsically ev...

Ngày tải lên: 30/03/2014, 21:20

6 390 0
Báo cáo khoa học: "USING %-CALCULUS TO REPRESENT IN LOGIC GRAMMARS" docx

Báo cáo khoa học: "USING %-CALCULUS TO REPRESENT IN LOGIC GRAMMARS" docx

... experience in natural language proc- essing is that inferencing is useful at all levels of processing, from words to entire texts. This points us toward something like the LC. The problem, of course, ... counter, to insure the same variable is never used twice. One way to do this in Prolog is to include 53 a place for the counter in each grarmnar predicate. This can b...

Ngày tải lên: 31/03/2014, 17:20

6 358 0
w