Tài liệu Báo cáo khoa học: "Integrating Syntactic Priming into an Incremental Probabilistic Parser, with an Application to Psycholinguistic Modeling" ppt

... 44th Annual Meeting of the ACL, pages 417–424,Sydney, July 2006.c2006 Association for Computational LinguisticsIntegrating Syntactic Priming into an Incremental Probabilistic Parser, with an ... Sturt, and Frank Keller. 2005. Paral-lelism in coordination as an instance of syntactic priming: Evidence from corpus-based modeling. In Proceedingsof the Human Language Technology Conference and ... method for incorporating priming into an incremental probabilis-tic parser. Three models are compared,which involve priming of rules betweensentences, within sentences, and withincoordinate structures....

Tài liệu Báo cáo khoa học: "Learning Syntactic Verb Frames Using Graphical Models" doc

... where a Bayesian model wasused to jointly induce syntactic and semantic classesfor verbs, although that study relied on manuallyannotated data and a predeﬁned SCF inventory andMLE. More recently, ... process to automatically deﬁne a probabilistic SCF inventory, we outperform systems with hand-crafted rules and inventories, using identical syntac-tic features. Second, by replacing the syntactic ... semi-automatic sources to link the syntax andsemantics of 5,726 verbs. FrameNet (Baker et al.,1998) provides semantic frames and annotated ex-ample sentences for 4,186 verbs. PropBank (Palmeret...

Tài liệu Báo cáo khoa học: "Exploring Syntactic Structural Features for Sub-Tree Alignment using Bilingual Tree Kernels" docx

... when translating a source span, any of its sub-spans is already translated. The STSG based de-coding can be easily performed with the STSSG decoder by restricting the translation rule set to be ... divergence, annota-tion discrepancy (Chinese parse tree employs a different grammar from Penn Treebank annota-tions) and degree of tolerance for parsing errors. Due to the above issues, we annotate ... parsed by Stanford parser (Klein and Manning, 2003) on both the English and Chinese sides. We manually annotate the sub-tree alignment for the automatically parsed tree pairs according to the definition...

Tài liệu Báo cáo khoa học: "Exploiting Syntactic and Shallow Semantic Kernels for Question/Answer Classiﬁcation" docx

... classifier can be used to re-rank the list of candidate answers of a QA sys-tem. Starting from the top answer, each instance canbe classified based on its correctness with respect to the question. ... impact of syntactic and shallowsemantic information in automatic classifi-cation of questions and answers and answerre-ranking. We define (a) new tree struc-tures based on shallow semantics encodedin ... relatedness between questions andanswers in answer re-ranking, to our knowledge nostudy uses kernel functions to encode syntactic in-formation. Moreover, the study of shallow semanticinformation such...

Tài liệu Báo cáo khoa học: "Discriminative Syntactic Language Modeling for Speech Recognition" pdf

... HumanLanguage Technology Conference and Meeting of the NorthAmerican Chapter of the Association for Computational Lin-guistics (HLT-NAACL), Edmonton, Canada.Andreas Stolcke and Jonathan Segal. ... Murat Saraclar, and Michael Collins. 2005. Dis-criminative n-gram language modeling. Computer Speechand Language. submitted.Brian Roark. 2001a. Probabilistic top-down parsing and lan-guage modeling. ... Geman, Steven Canon, Zhiyi Chi, andStefan Riezler. 1999. Estimators for stochastic “uniﬁcation-based” grammars. In Proc. ACL, pages 535–541.Daniel Jurafsky, Chuck Wooters, Jonathan Segal, AndreasStolcke,...

Tài liệu Báo cáo khoa học: "Integrating Information Extraction and Automatic Hyperlinking" docx

... due to the fact that edges in our automata are annotated by TFSs, instead of atomic symbols. However, not every outgoing edge in such an automaton must be analyzed, since TFS annota-tions can ... on the automaton transitions and thus exceed the strict locality of constraints in an atomic symbol approach. Further-more, coreferences serve as a means of information transport into the output ... for Japanese and Shanxi (Liu, 2000) for Chinese. The XTDL-based grammar engineering plat-form has been used to define grammars for English, German, French, Spanish, Chinese and Japanese allowing...

Tài liệu Báo cáo khoa học: "A Syntactic Framework for Speech Repairs and Other Disruptions" doc

... of machine translators and meeting analysis programs that deal with human-human dialog. Speech recognizers have started to adapt to spoken dialog (ver- sus read speech). Recent language mod- ... utterances. So for the partial utterance, take the ban- um the oranges, three constituents would be produced, one for urn, another for take the ban-, and a third for take the oranges. Another ... utterance, or 3) continue an utterance that was left hanging at the last change of speaker (e.g., because of an ac- knowledgment). Note that a speaker may try to interrupt another speaker and...

Tài liệu Báo cáo khoa học: "INTEGRATING WITH WORD BOUNDARY IDENTIFICATION SENTENCE UNDERSTANDING" docx

... Chinese and Oriental Languages, 4(1):33-56. Fano, R. (1961) Transmission of information. MIT Press, Cambridge MA. Goldman, R. (1990) A probabilistic approach to language understanding. ... into the model We will derive this information from a corpus of 46,520 words of to- tal usage frequency of 13019,814 given to us by Liang Nanyuan of the Beijing University of Aeronautics and ... hai and zi in (1) and evaluate their associative strength as equal to 13.34. This association is so strong that another codelet will be called upon to group these two characters into a word-structure,...

Tài liệu Báo cáo khoa học: "Arabic Syntactic Trees: from Constituency to Dependency" ppt

... cameras and the lenses of photog-raphers as he was getting on the bus.Its respective representations in Figures 1 and 2use glossed tokens which are further split into morphemes and transliterated ... de-pendency tree, and (ii) a procedure as-signing analytical functions to the nodesof the dependency tree.Apart from an outline of the annota-tion schemes and a deeper insight into these procedures, ... intend to share the resourcesthey create. Prior to this exchange, 10,000 wordsfrom the LDC Arabic Newswire A Corpus weremanually annotated in both syntactic styles as astep to ensure that the annotations...

Tài liệu Báo cáo khoa học: "Integrating Symbolic and Statistical Representations: The Lexicon Pragmatics Interface" pot

... (3b) with the highest probability: i.e., the one where cotton bag means bag made of cotton. Then similarly to (5), Assume Coherence, Subtype and Elaboration are used to infer that the cotton ... her clothes into various large bags. b. She put her skirt in the cotton bag. (4) a. Mary sorted her clothes into various bags made from plastic. b. She put her skirt into the cotton bag. If ... Fr/ihlingsanfang * January half * spring beginning half of January beginning of spring Figure 1: Some German compounds with non-compound translations mantics and pragmatics in determining meaning. We...

Xem thêm