Báo cáo khoa học: "Modeling with Structures in Statistical Machine Translation" pot

... tion we are more interested in cross-linguistic structures, similar to the case of using interlin- gua to represent cross-linguistic information in knowledge-based MT. To obtain structures that ... words/phrases. Since the algorithm only uses a monolin- gual corpus, it often introduces some language- specific structures resulting from biased usages of a specific language. In...

Ngày tải lên: 08/03/2014, 06:20

... looking at the succeeding context according to P b (w m 1 ) = m  i=1 P (w i |w m i+1 ) ≈ m  i=1 P (w i |w i+n−1 i+1 ) (2) 3.1 Training For the convenience of training, we invert the or- der in ... Computational Linguistics, pages 1288–1297, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Enhancing Language Models in Statistical Machine Translati...

Ngày tải lên: 07/03/2014, 22:20

... DEALING WITH CONJUNCTIONS IN A MACHINE TRANSLATION ENVIRONMENT Xiumlng HUANG Institute of Linguistics Chinese Academy of Social Sciences BeiJing, China* ABSTRACT The paper ... grouping of sentences containing coordinate conjunctions. Finally, the algorithm is described in Section 3. I GAPPING, RIGHT NODE RAISING AND REDUCED CONJUNCTION I.I Gapping Gapping is ... an English...

Ngày tải lên: 08/03/2014, 18:20

... DEALING WITH CONJUNCTIONS IN A MACHINE TRANSLATION ENVIRONMENT Xiuming Huang Institute of Linguistics chinese Academy of Social Sciences Beijing, China* ABSTRACT A set ... lacks the power for resolving the ambiguities con- tained in structures like (1). In the machine translation system designed by (Nagao et al 82), when dealing with conjunctions, only the ... coordi...

Ngày tải lên: 01/04/2014, 00:20

... consti- tutes our MCC baseline. Regarding the reranker, we divided the training set in two chunks of data: Train1 and Train2. The binary classifiers are trained on Train1 and tested on Train2 (and vice versa) ... according to the number of hypotheses (child-free setting). using the complete hierarchy as representation, i.e., up to five times in training and eight time in test- ing. This i...

Ngày tải lên: 23/03/2014, 14:20

... stating the information under FUNCTOR]SYNSEM instead. In the first stage X2MORF processes the morpho- tactic information including the word-form-specific morphosyntactic information making ... associated with it lezeme. There are problems with such a static view of the lexicon. In the open word classes our vocabulary is potentially infinite. Making use of derivation and compou...

Ngày tải lên: 01/04/2014, 00:20

... Trigger-Based Lexicon Models. In: Pro- ceedings of EMNLP, Singapore. F. Och. 2003. Minimum error rate training in statistic- al machine translation. In: Proceedings of ACL. Sapporo, Japan. S. Pado ... training corpus), the context will be the words instantiating the non-terminals. In turn, the context for the sub-phrases that instantiate the non-terminals will be the words in...

Ngày tải lên: 20/02/2014, 04:20

... 2009. Joint Decoding with Multiple Translation Models. In Proceedings of the Association for Computational Linguistics, pages 576-584. Franz Och. 2003. Minimum Error Rate Training in Sta- tistical ... Statistical Machine Translation. In Proceedings of the Association for Computational Linguistics, pages 521-528. Yang Ye, Ming Zhou, and Chin-Yew Lin. 2007. Sen- tence Level...

Ngày tải lên: 07/03/2014, 22:20

... accomplished by introduc- ing two additional features into the MT model which operate on the existing rules of the grammar, with- out introducing competing rules. These features are treated, both in feature-weight ... extracting grammar rules, we gathered WSD training data by following the proce- dure described in section 4. 6.1 Hiero Results Using the MT 2002 test set, we ran the minim...

Ngày tải lên: 08/03/2014, 02:21

... language sentences. 3 Interactive Machine Translation In a statistical approach, the problem of finding an extension ef +1 of a given prefix 61 can be de- scribed by constraining the search to ... of statis- tical machine translation. In interactive machine translation, the basic idea is to provide an environ- ment to a human translator that interactively reacts upon the input a...

Ngày tải lên: 08/03/2014, 21:20