Báo cáo khoa học: "Phrase Table Training For Precision and Recall: What Makes a Good Phrase and a Good Phrase Pair?" doc

... tasks or ap- plications such as information extraction, ques- tion answering, and machine translation (Surdea- nu et al., 2003). Several CoNLL shared tasks (Carreras and Marquez, 2005; Surdeanu ... amount of natural language text available at a low cost. Semi-supervised me- thods compensate the scarcity of labeled data by utilizing an additional and much larger amount of unlabeled...

Ngày tải lên: 07/03/2014, 22:20

... 2 Iteration Manually Prepared Training Data for Language 1 Classifier Classifier Training Training Enlarged Training Data for Language 1 Enlarged Training Data for Language 2 Manually Prepared Training ... Data for Language 2 ClassifierClassifier Further Enlarged Training Data for Language 1 Further Enlarged Training Data for Language 2 Translate reliable parts of cl...

Ngày tải lên: 08/03/2014, 00:20

... Tagger Drahom ´ ıra “johanka” Spoustov ´ a Jan Haji ˇ c Jan Raab Miroslav Spousta Institute of Formal and Applied Linguistics Faculty of Mathematics and Physics, Charles University Prague, Czech ... and “un- supervised” data for “manually annotated” and “(automat- ically annotated) plain (raw) text” data, respectively, even though these adjectives are meant to describe the process...

Ngày tải lên: 17/03/2014, 22:20

... California 4676 Admiralty Way, Suite 1001 Marina del Rey, CA 90292 marcu@isi.edu Abstract We introduce a semi-supervised approach to training for statistical machine transla- tion that alternates ... semi-supervised learning. 2 Data Sets and Baseline We conduct experiments on alignment and translation tasks using Arabic/English and French/English data sets (see Table 1 for det...

Ngày tải lên: 31/03/2014, 01:20

... available for system development and also serve as training data for machine learning approaches. Using the discriminant-based Redwoods approach to tree- banking (Oepen, Flickinger, Toutanova, ... Using a trial LFG treebank for Norwegian (of less than 100 annotated sen- tences), we have adapted the tools for the current LOGON version and are now working to train on larger data...

Ngày tải lên: 20/02/2014, 12:20

... of ACL-08: HLT, pages 81–88, Columbus, Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Phrase Table Training For Precision and Recall: What Makes a Good Phrase and a Good ... retrieval, precision and recall issues need to be addressed with a right balance for building a phrase translation table. High precision requires tha...

Ngày tải lên: 08/03/2014, 01:20

... translation models for phrase- based statistical machine translation (SMT) systems (Koehn et al., 2003) takes unaligned bilingual train- ing data as input, and outputs a scored table of phrase pairs. ... Joint Phrase Alignment and Extraction Graham Neubig 1,2 Taro Watanabe 2 , Eiichiro Sumita 2 , Shinsuke Mori 1 , Tatsuya Kawahara 1 1 Graduate School of Informatics, Kyoto Univ...

Ngày tải lên: 20/02/2014, 04:20

... the ACL 2007 Demo and Poster Sessions, pages 65–68, Prague, June 2007. c 2007 Association for Computational Linguistics An Approximate Approach for Training Polynomial Kernel SVMs in Linear ... Central University National Central University Ming Chuan University Taoyuan, Taiwan Taoyuan, Taiwan Taoyuan, Taiwan bcbb@db.csie.ncu.edu.tw yang@cl.ncu.edu.tw lees@mcu.edu.tw Abstract...

Ngày tải lên: 20/02/2014, 12:20

... collocations, and verb alternations), 496 and for NLP applications in sparse data situations. In this paper, we provide an evaluation based on a language model. The remainder of the paper is organised as ... verb alternations, and collocations, and (ii) as a lexical resource for the statistical disambiguation of parse trees. References Steven Abney and Marc Light. 1999. Hidi...

Ngày tải lên: 08/03/2014, 01:20

... semantically similar phrases. Another method is to use multi-parallel corpora (Cohn and Lapata, 2007; Utiyama and Isahara, 2007) to im- prove phrase coverage and translation quality. This paper ... incorporation by performing par- tial matching for phrase translation before decod- ing. The advantage is that the main search algorithm need not be changed. For a source phrase ...

Ngày tải lên: 08/03/2014, 01:20