Báo cáo khoa học: "MACHINE TRANSLATION : WHAT TYPE OF POST-EDITING ON WHAT TYPE OF DOCUMENTSFOR WHAT TYPE OF USERS" pdf
... MACHINE TRANSLATION : WHAT TYPE OF POST-EDITING ON WHAT TYPE OF DOCUMENTS FOR WHAT TYPE OF USERS Anne-Marie LAURIAN Centre National de la Recherche Scientifique Universitd de la Sorbonne Nouvelle ... one has of what a translation should be. Translation can only be defined in particular situations, regarding particular documents. And machine translatio...
Ngày tải lên: 08/03/2014, 18:20
... match” POS tag pairs. y Word translation probability: P( | ) ji fe. y Rank: the rank of the word to word probabil- ity of j f in as a translation of i e among all the foreign words in the ... S ynchronous Dependency Insertion Grammars Ding and Palmer (2004b) described one version of synchronous grammar: Synchronous Dependency Insertion Grammars. A Dependency Insertion Gr...
Ngày tải lên: 20/02/2014, 15:20
Ngày tải lên: 21/02/2014, 20:20
Tài liệu Báo cáo khoa học: " Machine Translation already does Work" doc
... in front of a screen watching the machine at work. In a different situation, however, where what is required is very high quality translation, and where the volume of translation to be done ... task of translation, so the need for machine translation is different, depending on the particular characteristics of individual situations. Here, so many factors come into dete...
Ngày tải lên: 21/02/2014, 20:20
Báo cáo khoa học: "Machine Translation System Combination by Confusion Forest" docx
... constructing a confu- sion forest: First, MT outputs are parsed. Second, Initialization: [TOP → •S, 0] : ¯ 1 Scan: [X → α •xβ, h] : u [X → αx •β, h] : u Predict: [X → α •Yβ, h] [Y → •γ, h + 1] : u Y u → ... Experiments are presented in Section 5 followed by discussion and our conclu- sion. 2 Combination by Confusion Network The system combination framework based on confu- si...
Ngày tải lên: 07/03/2014, 22:20
Tài liệu Báo cáo khoa học: "Name Translation in Statistical Machine Translation Learning When to Transliterate" pptx
... restrictions. 1. :: q == :: 0 2. :: ough == :: 0 3. :: ch == :[ aou] ,:: 0.1 4. :: k == , $:, $:: 0.1 ; :: 0.2 5. :: == :, EC :: 0 .1 The first example rule above assigns to the straightforward pair /q a cost of 0. ... translit cost(e,f) 3.1 Indexing with consonant skeletons We identify a list of English transliteration candi- dates through what we cal...
Ngày tải lên: 20/02/2014, 09:20
Tài liệu Báo cáo khoa học: Parvalbumin deficiency in fast-twitch muscles leads to increased ‘slow-twitch type’ mitochondria, but does not affect the expression of fiber specific proteins doc
... In addition, increased transcription of mitochond- rial genes has been observed as the result of permanent activation of some components of Ca 2+ signaling pathways [13,14,24]. Based on this, ... & Cuezva JM (1997) Control of the trans- lational efficiency of beta-F1-ATPase mRNA depends on the regulation of a protein that binds the 3¢ untrans- lated region of the mRNA....
Ngày tải lên: 19/02/2014, 07:20
Tài liệu Báo cáo khoa học: "Sentiment Translation through Lexicon Induction" doc
... translations of each other but instead often fell into the categories of hyponymy, hypernomy, holonymy, or meronymy. However, this makes the similarity values appli- cable for the translation of sentiment ... induction of a sentiment lexicon is the sub- ject of early work by (Hatzivassiloglou and McK- eown, 1997). They construct graphs from coor- dination data from large corpora b...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Crowdsourcing Translation: Professional Quality from Non-Professionals" pptx
... comparison of professional translations provided by the LDC to non-professional translations created on Mechanical Turk. get high quality translations in aggregate by solicit- ing multiple translations, ... Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Crowdsourcing Translation: Professional Quality from Non-Professionals Omar F. Zaidan and Chris Callison-Bu...
Ngày tải lên: 20/02/2014, 04:20
Tài liệu Báo cáo khoa học: "Unsupervised Translation Induction for Chinese Abbreviations using Monolingual Corpora" ppt
... Value number of English entities 5M number of Chinese entities 4.7M number of full-abbreviation relations 51K number of translation entries added 210K total number of translation entries 50M Table 3: Statistics ... components: identifying abbreviations, learning their full-forms, inducing their translations, and integrating the abbreviation translations into the baseline SMT...
Ngày tải lên: 20/02/2014, 09:20