Báo cáo khoa học: "Re-Ranking Models For Spoken Language Understanding Marco Dinarelli University of Trento Italy" potx

... Spoken Language Understanding Marco Dinarelli University of Trento Italy dinarelli@ disi.unitn.it Alessandro Moschitti University of Trento Italy moschitti@disi.unitn.it Giuseppe Riccardi University ... Proceedings of the 12th Conference of the European Chapter of the ACL, pages 202–210, Athens, Greece, 30 March – 3 April 2009. c 2009 Association for Computat...

Ngày tải lên: 08/03/2014, 21:20

Ngày tải lên: 31/03/2014, 17:20

... the ideas of Grosz and Sidner (1986), but refor- mulates them specifically for the task of narra- tive understanding. A reformulation, I believe, is needed because different genres of discourse ... TEMPORAL REASONING IN NATURAL LANGUAGE UNDERSTANDING: THE TEMPORAL STRUCTURE OF THE NARRATIVE Alexander Nakhimovsky Department of Computer Science Colgate University Hami...

Ngày tải lên: 18/03/2014, 02:20

... Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 115–119, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Topic Models ... number of occurrences of the word pair in s. Topic Modeling for MT We extend provenance to cover a set of automatically generated topics z n . Given a parallel tra...

Ngày tải lên: 19/02/2014, 19:20

... this paper are for Arabic-English machine translation of news stories. We also present a novel method for measuring word order similarity (or differences) between any given pair of languages based ... 3. The rest of this paper is organized as follows. Sec- tion 2 presents a review of related work. In Section 3 we propose a method for measuring the distortion be- tween any given...

Ngày tải lên: 08/03/2014, 02:21

... to determine the sentiment flow of authors in reviews. Here we show that fine-to-coarse models of senti- ment can often be reduced to the sequential case. Cascaded models for fine-to-coarse sentiment analysis ... more complex hierarchical models. The advantage of using hierarchical models of this form is that they are nested, which keeps in- ference tractable. Observe that each...

Ngày tải lên: 08/03/2014, 02:21

... Aist Department of Brain Center for the Study of Language  RIACS  and Cognitive Sciences  and Information (CSLI) NASA Ames Research Center,  University of Rochester  Stanford University  Moffet Field, ... a grammar-based language model and assist users in becoming expert as quickly as possible. This approach takes advantage of the strengths of both types of langua...

Ngày tải lên: 08/03/2014, 21:20

... be employed in informa- tion retrieval. Furthermore, given a sentence aligned parallel corpus of two languages and al- most parse information for the sentences of one of the languages, one ... Proceedings of EACL '99 New Models for Improving Supertag Disambiguation John Chen* Department of Computer and Information Sciences University of Delaware Newark, DE 197...

Ngày tải lên: 08/03/2014, 21:20

... from a natural language ex- pression, E, into an equivalent expression, F, in an unambigous formal language. Typically, this for- mal language will be hand-crafted to enhance per- formance on ... terms of the form p(nlf), where n is the number of clumps generated by the formal lan- guage word f. The resulting model can be trained automatically from a bilingual corpus of Eng...

Ngày tải lên: 08/03/2014, 21:20

... Kevin Knight University of Southern California Information Sciences Institute Marina del Rey, California 90292 {sravi,knight}@isi.edu Abstract We describe a novel method for the task of unsupervised ... been shown to work for natural language applications. These approaches employ heuristic search methods with MDL for the task of unsupervised learning of morphology of natu-...

Ngày tải lên: 17/03/2014, 01:20