Báo cáo khoa học: "Using POS Information for Statistical Machine Translation into Morphologically Rich Languages" doc

... Using POS Information for Statistical Machine Translation into Morphologically Rich LanguagesNicola Ueffing and Hermann NeyLehrstuhl ftir Informatik VI - Computer Science ... including baseform and POS information for translation from German into English. Information contained in the German en-tries that are not relevant for the generation ofthe English translation ... (e.g. 'esta' into 'estar P3S'). This would require postprocess-ing tools that are able to generate the correct verbform from the baseform and the person and tense information. Table...

Báo cáo khoa học: "Pre- and Postprocessing for Statistical Machine Translation into Germanic Languages" docx

... 2011.c2011 Association for Computational LinguisticsPre- and Postprocessing for Statistical Machine Translation into GermanicLanguagesSara StymneDepartment of Computer and Information ScienceLink¨oping ... research on translation out of English, or be-tween other language pairs. Methods that are useful for translation into English have problems in manycases, for instance for translation into morpholog-ically ... analysis of ma-chine translation output, which can both moti-vate and evaluate the studies performed.1 Introduction Statistical machine translation (SMT) is based ontraining statistical models...

Tài liệu Báo cáo khoa học: "Bilingual Sense Similarity for Statistical Machine Translation" ppt

... Therefore, questions emerge: how good is the sense similarity computed via VSM for two units from parallel corpora? Is it useful for multi-lingual applications, such as statistical machine translation ... source and target sides of a translation rule to improve statistical machine translation perfor-mance. This work attempts to measure directly the sense similarity for units from different languag-es ... addi-tional features of the translation model to im-prove translation performance. Significant im-provements are obtained over a state-of-the-art hierarchical phrase-based machine translation system....

Báo cáo khoa học: "Hypothesis Mixture Decoding for Statistical Machine Translation" ppt

... for 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 Machine Translation ... including: 8 n-gram posterior features computed from PB/DHPB forests for ; 8 stemmed n-gram posterior features computed from stemmed PB/DHPB forests for ; 4 n-gram post-erior features ... end for 12: end for 13: for each hypothesis  do 14: compute HM decoding features for  15: add  to  16: end for 17: for...

Báo cáo khoa học: "Randomised Language Modelling for Statistical Machine Translation" doc

... 2007.c2007 Association for Computational LinguisticsRandomised Language Modelling for Statistical Machine Translation David Talbot and Miles OsborneSchool of Informatics, University of Edinburgh2 ... 1) for j = 1 to qc(x) do for i = 1 to k dohi(x) ← hash of event {x, j} under hiBF[hi(x)] ← 1end for end for end for return BF3.1 Log-frequency Bloom ﬁlterThe efﬁciency of our scheme for ... sizes.BF for various order n-gram sets from the Giga-word Corpus with the same underlying false posi-tive rate (0.125). The additional space required byour scheme for storing frequency information...

Báo cáo khoa học: "Filtering Syntactic Constraints for Statistical Machine Translation" pdf

... Tree-to-string alignment template for statistical machine translation. In ACL-COLING. Daniel Marcu, Wei Wang, Abdessamad Echihabi, and Kevin Knight. 2006. SPMT: Statistical machine translation with syntactified ... imperfect reordering constraints for statis-tical machine translation. A lot of effort has been made for soft applications of syntactic constraints. We alternatively propose the se-lective use of ... 2010.c2010 Association for Computational LinguisticsFiltering Syntactic Constraints for Statistical Machine Translation Hailong Cao and Eiichiro Sumita Language Translation Group, MASTAR...

Báo cáo khoa học: "Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability" pptx

... conclude by suggestingnew best practices for signiﬁcance testing for ma-chine translation. 2 Nondeterminism and OtherOptimization Pitfalls Statistical machine translation systems consist of amodel ... experimen-tal outcomes, and make recommendations for reporting results more accurately.1 IntroductionThe need for statistical hypothesis testing for ma-chine translation (MT) has been acknowledged sinceat ... can account for substantial amount of variationin translation quality,2which, if not controlled for, could lead to incorrect conclusions. We then showthat it is possible to control for this...

Báo cáo khoa học: "Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability" pdf

... Association for Computational Linguistics:shortpapers, pages 182–187,Portland, Oregon, June 19-24, 2011.c2011 Association for Computational LinguisticsBayesian Word Alignment for Statistical Machine ... Initialize A2 for k = 1 to K do3 for each sentence-pair s in (E, F) do4 for j = 1 to J do5 for i = 0 to I do6 Calculate P (aj= i| · · · )according to (7)7 Sample a new value for ajTable ... code for Bayesian inference and6International Workshop on Spoken Language Translation. http://iwslt2010.fbk.eu7Using only the ﬁrst English reference for symmetry.8Workshop on Machine Translation. http://www.statmt.org/wmt10 /translation- task.html184Method...

Tài liệu Báo cáo khoa học: "Using Structural Information for Identifying Similar Chinese Characters" pdf

... characters form a Chinese word to carry a meaning, although there are Chinese words that contain only one Chinese character. For in-stance, a translation for “conference” is “研討會” and a translation ... pronunciations or in their internal structures are useful for computer-assisted language learning and for psycholinguistic studies. Al-though it is possible for us to employ image-based methods to identify ... Volume), pages 93–96,Columbus, Ohio, USA, June 2008.c2008 Association for Computational LinguisticsUsing Structural Information for Identifying Similar Chinese Characters Chao-Lin Liu Jen-Hsiang...

Báo cáo khoa học: "Using Bilingual Information for Cross-Language Document Summarization" pptx

... Chinese-side information is more benefi-cial than the English-side information. 2) The Chinese-side information and the Eng-lish-side information can complement each other. 3) The proposed CoRank ... side. Two typical translation schemes are document translation or summary translation. The document translation scheme first translates the source documents into the corresponding docu-ments in ... information from the original documents in the source language or the infor-mation from the translated documents in the target language. In this study, we propose to use the bilingual information...

Xem thêm