Báo cáo khoa học: "Collaborative Decoding: Partial Hypothesis Re-ranking Using Translation Consensus between Decoders" docx

... Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Collaborative Decoding: Partial Hypothesis Re-ranking Using Translation Consensus between Decoders Mu Li 1 , Nan Duan 2 , Dongdong Zhang 1 , ... the performance gain due to partial hypothesis re-ranking. Be- cause Equation 3 is a general model that can be applied to both partial hypothesis and n-best (full hypoth...

Ngày tải lên: 23/03/2014, 16:21

... Computational Linguistics Improving On-line Handwritten Recognition using Translation Models in Multimodal Interactive Machine Translation Vicent Alabau, Alberto Sanchis, Francisco Casacuberta Institut ... interactive machine translation (IMT), a hu- man expert is integrated into the core of a ma- chine translation (MT) system. The human ex- pert interacts with the IMT system by par...

Ngày tải lên: 07/03/2014, 22:20

... when split. Using this model the number of compound parts that were produced in the wrong order was reduced drastically compared to not using a part-of-speech sequence model for translation into ... machine translation in four problem areas, using several methods of pre- and postprocessing. References Alexandra Birch, Miles Osborne, and Philipp Koehn. 2008. Predicting success in mac...

Ngày tải lên: 23/03/2014, 16:20

... value was selected using a tuning set (Section 3.1). The unsu- pervised setup, Model III, is similar to the semi- supervised setup except that the EM algorithm is initialized using an informed ... it was our hypothesis that a multivariate distribu- tion such as MVN which can capture the covari- ance amongst the features will be a better fit. The above finding confirms this hypothes...

Ngày tải lên: 31/03/2014, 00:20

... the calculation. sumes that a good translation of it is “Well heard , it talking a beautiful victory” because the best translation of “bien” is “well”, the best translation of “entendu” is “heard”, ... (PME): , but is not a perfect translation. deadly search error (DSE): , and while is a perfect translation, while is not. fortuitous search error (FSE): , and is a perfect translation...

Ngày tải lên: 20/02/2014, 18:20

... generic translation tools. We propose the demonstration of an end-to-end tool integrated in the HAL open archive for enabling efficient translation for scientific texts. This tool can give translation ... train- ing corpus. The actual translation of the pa- per is performed using adapted translation as described in Section 4. • The translation process generates a bilingual TEI for...

Ngày tải lên: 22/02/2014, 03:20

... models. Typically, by using the GHKM algorithm (Galley et al. 2004), translation rules are learned from word-aligned bilingual texts whose source side has been parsed by using a syntactic parser. ... string. A deriva- tion is a sequence of translation steps (i.e., the use of translation rules). Figure 1 shows an example derivation d that performs translation over a Chinese s...

Ngày tải lên: 17/03/2014, 00:20

... Introduction System combination aims to find consensus trans- lations among different machine translation sys- tems. It proves that such consensus translations are usually better than the output ... space of each model as a translation hypergraph (Section 3.1), our joint decoder packs individual translation hypergraphs together by merging nodes that have identical partial translati...

Ngày tải lên: 23/03/2014, 16:21

... translation software ! " # $ % & machine translation software ! " # $ % & Figure 1: Segmentation ambiguity in phrase-based MT: two different segmentations lead to the same translation ... D(x) yields some translation string y = Y(d) in the target language. We write D(x, y) def = {d ∈ D(x) : Y(d) = y} to denote the set of all derivations that yield y. Thus, the set of...

Ngày tải lên: 23/03/2014, 16:21

... on coarse-to-fine inference for ma- chine translation (Petrov et al., 2008). 7 Experiments We report experiments on translation from Chinese to English, using the tree-to-string model described 8 In ... 38(1):127–138. Slav Petrov, Aria Haghighi, and Dan Klein. 2008. Coarse-to-fine syntactic machine translation using lan- guage projections. In Proceedings of the 2008 Confer- ence on Em...

Ngày tải lên: 30/03/2014, 21:20