Tài liệu Báo cáo khoa học: " Machine Translation already does Work" doc

... FORUM ON MACHINE TRANSLATION Machine Translation already does Work Margaret King ISSCO 54, rte des Acacias CH-1227 Geneva, Switzerland ... know it or not, need different kinds of machine translation systems. Now we can return to the original question: machine translation works when the machine translation system is able to resolve ... answering a question like...

Ngày tải lên: 21/02/2014, 20:20

Ngày tải lên: 21/02/2014, 20:20

... the baseline sys- tem based on the IBM models in both translation speed and quality. 1 Introduction Statistical approaches to machine translation, pio- neered by (Brown et al., 1993), achieved ... using the IBM Model 1 (Brown et al., 1993) word to word translation probability as the ET translation probability. y Smoothing the ET translation probabilities. The LM probabilities...

Ngày tải lên: 20/02/2014, 15:20

... then projected to the target language. Problems arise due to mistranslations, e.g., because irony is not recognized. Banea et al. (2008) use machine translation for multilingual sentiment analysis. Given ... Linguistics Sentiment Translation through Lexicon Induction Christian Scheible Institute for Natural Language Processing University of Stuttgart scheibcn@ims.uni-stuttgart.de Abstra...

Ngày tải lên: 20/02/2014, 04:20

... disambiguates speech acts. The final goal is to improve translation quality in a speech-to-speech translation system. 1 Ambiguity in Speech Translation For any given utterance out of what we can ... goal of improv- ing the translation in an end-to-end speech transla- tion system. The work described was conducted within the JANUS multi-lingual speech-to-speech translation sy...

Ngày tải lên: 22/02/2014, 03:20

... names in par- ticular is clearly valuable to the human reader of machine translated documents as well as for sys- tems using machine translation for further informa- tion processing. At the same ... translation accuracy than 3 out of 4 professional translators. The paper also includes a discussion of challenges in name translation evaluation. 1 Introduction State-of-the-art statisti...

Ngày tải lên: 20/02/2014, 09:20

... this translation. • Is-Best percentage: how often the translation was top-ranked among the four translations. • Is-Better percentage: how often the translation was judged as the better translation, ... for parsing-based machine translation with syn- tax, semirings, discriminative training and other good- ies. In Proceedings of the Joint Fifth Workshop on Sta- tistical Machine Tr...

Ngày tải lên: 20/02/2014, 04:20

... AAMT language m odel 0.137 0.133 phrase translation 0.066 0.023 lexical translation 0.061 0.078 reverse phrase translation 0.059 0.103 reverse lexical translation 0.112 0.090 phrase penalty -0.150 ... natural ways to integrate the ab- breviation translation component with the baseline translation system. This is critical to make the ab- breviation translation get performance gai...

Ngày tải lên: 20/02/2014, 09:20

... partitions with the same score will have the same rank. 160 Training Corpus Test Corpus # Docs # Tokens # Docs # Tokens BNEWS 216 67470 51 18357 NPAPER 76 71944 17 18174 NWIRE 130 85688 29 20528 Table ... classification task. Specifically, a clas- sifier is first trained to determine whether two NPs in a document are co-referring or not. A separate clustering mechanism then coordinates the possib...

Ngày tải lên: 20/02/2014, 15:20

... corpus, and the accuracy of choosing the major translation for the last word has already exceeded 98%. We next applied BB, MB-B, and MB-D to word translation disambiguation. The experiment settings ... address here the problem of word translation disambiguation. For instance, we are concerned with an ambiguous word in English (e.g., ‘plant’), which has multiple translations i...

Ngày tải lên: 20/02/2014, 21:20