Báo cáo khoa học: "A Translation Aid System with a Stratified Lookup Interface" doc

Báo cáo khoa học: "A Translation Aid System with a Stratified Lookup Interface" doc

Báo cáo khoa học: "A Translation Aid System with a Stratified Lookup Interface" doc

... ACL 2007 Demo and Poster Sessions, pages 5–8, Prague, June 2007. c 2007 Association for Computational Linguistics A Translation Aid System with a Stratified Lookup Interface Takeshi Abekawa and ... Kageura Library and Information Science Course Graduate School of Education, University of Tokyo, Japan {abekawa,kyo}@p.u-tokyo.ac.jp Abstract We are currently developing a trans...

Ngày tải lên: 23/03/2014, 18:20

4 236 0
Báo cáo khoa học: "Consistent Translation using Discriminative Learning: A Translation Memory-inspired Approach" pdf

Báo cáo khoa học: "Consistent Translation using Discriminative Learning: A Translation Memory-inspired Approach" pdf

... phrase-based SMT, translation models and lan- guage models are automatically learned and/or gen- eralised from the training data, and a translation is produced by maximising a weighted combination ... decide to mark up the input sentence if the translations of the marked phrases are accurate when taken contextual information into account. As large-scale manually annotated data is not...

Ngày tải lên: 07/03/2014, 22:20

10 305 0
Báo cáo khoa học: "Ordering Prenominal Modifiers with a Reranking Approach" potx

Báo cáo khoa học: "Ordering Prenominal Modifiers with a Reranking Approach" potx

... Modifiers with a Reranking Approach Jenny Liu MIT CSAIL jyliu@csail.mit.edu Aria Haghighi MIT CSAIL me@aria42.com Abstract In this work, we present a novel approach to the generation task of ordering ... probability is above a certain threshold then they say that a precedes b. Shaw and Hatzivassiloglou also use a transitivity method to fill out parts of the Count table where bigrams...

Ngày tải lên: 30/03/2014, 21:20

8 333 0
Báo cáo khoa học: "Building Deep Dependency Structures with a Wide-Coverage CCG Parser" ppt

Báo cáo khoa học: "Building Deep Dependency Structures with a Wide-Coverage CCG Parser" ppt

... the data. If a word ap- pears at least K times in the data, the supertagger only considers categories that appear in the word’s category set, rather than all lexical categories. The second parsing ... Adjoining Grammar as an alternative to context-free grammar, and here we use another “mildly context-sensitive” for- malism, Combinatory Categorial Grammar (CCG, Steedman (2000)), which arguab...

Ngày tải lên: 31/03/2014, 06:20

8 260 0
Báo cáo khoa học: "Approximating Context-Free Grammars with a Finite-State Calculus" docx

Báo cáo khoa học: "Approximating Context-Free Grammars with a Finite-State Calculus" docx

... grammar. An exam- ples is: S ~ al S S~al A1 S-+anS S-+anAn A~ -+ a~ X A2 + al A2 An -~ al An X-+e A1 -+ a2 Az A1 ~ an A1 A2 -+ a2 X A2 ~ an A2 An -+ a2 A, ~ An ~ an X Here the grammar ... context-free grammars because context-free lan- guages are the smallest class of formal language that can realistically be applied to the analysis of natural language. Techniques suc...

Ngày tải lên: 31/03/2014, 21:20

8 196 0
Báo cáo khoa học: "Coarse Lexical Semantic Annotation with Supersenses: An Arabic Case Study" docx

Báo cáo khoa học: "Coarse Lexical Semantic Annotation with Supersenses: An Arabic Case Study" docx

... International Conference on Data Mining, pages 485–496, Sparks, Nevada, USA, May. Society for Industrial and Applied Mathematics. Rebecca J. Passonneau, Ansaf Salleb-Aoussi, Vikas Bhardwaj, and Nancy ... 2005; Ciaramita and Altun, 2006; Paaß and Reichartz, 2009), as well as for Italian (Picca et al., 2008; Picca et al., 2009; Attardi et al., 2010) and Chinese (Qiu et al., 2011), languages wi...

Ngày tải lên: 16/03/2014, 20:20

6 468 0
Báo cáo khoa học: "Bayesian Unsupervised Word Segmentation with Nested Pitman-Yor Language Modeling" doc

Báo cáo khoa học: "Bayesian Unsupervised Word Segmentation with Nested Pitman-Yor Language Modeling" doc

... Pitman-Yor Language Modeling Daichi Mochihashi Takeshi Yamada Naonori Ueda NTT Communication Science Laboratories Hikaridai 2-4, Keihanna Science City, Kyoto, Japan {daichi,yamada,ueda}@cslab.kecl.ntt.co.jp Abstract In ... experiments on standard datasets for Chinese and Japanese word segmentation that are publicly available, as well as the same dataset used in (Goldwater et al., 2006). Note...

Ngày tải lên: 17/03/2014, 01:20

9 238 0
Tài liệu Báo cáo khoa học: "Exploiting Readymades in Linguistic Creativity: A System Demonstration of the Jigsaw Bard" docx

Tài liệu Báo cáo khoa học: "Exploiting Readymades in Linguistic Creativity: A System Demonstration of the Jigsaw Bard" docx

... of adjectival proper- ties. The phrase “wet haddock” is a readymade for coldness because “wet” accentuates the “cold” that we associate with “haddock” (via the web simile “as cold as a haddock”). ... property A such that the simile “as A as P” is a meaningful and memorable comparison? The property A can be simple, as in “as dark as a chocolate espresso”, or complex, as in “as...

Ngày tải lên: 20/02/2014, 05:20

6 442 0
Báo cáo khoa học: Unconventional translation initiation of human trypsinogen 4 at a CUG codon with an N-terminal leucine A possible means to regulate gene expression pdf

Báo cáo khoa học: Unconventional translation initiation of human trypsinogen 4 at a CUG codon with an N-terminal leucine A possible means to regulate gene expression pdf

... necessar- ily mean that translation starts from a downstream AUG, as predicted by genome and mRNA analysis, but raises the possibility that the translated form may have used a CUG start codon with ... with an N-terminal leu- cine amino acid. Our present study indicates that non- AUG translation initiation may be operable more often than anticipated. This may have a great impact...

Ngày tải lên: 07/03/2014, 10:20

11 469 0
Báo cáo khoa học: "Machine Translation System Combination by Confusion Forest" docx

Báo cáo khoa học: "Machine Translation System Combination by Confusion Forest" docx

... Combination by Confusion Forest Taro Watanabe and Eiichiro Sumita National Institute of Information and Communications Technology 3-5 Hikaridai, Keihanna Science City, 619-0289 JAPAN {taro.watanabe,eiichiro.sumita}@nict.go.jp Abstract The ... Workshop on Statistical Machine Translation and MetricsMATR, pages 17–53, Uppsala, Sweden, July. Revised August 2010. David Chiang. 2007. Hierarchical...

Ngày tải lên: 07/03/2014, 22:20

9 256 0
Từ khóa:
w