Báo cáo khoa học: "Subsentential Translation Memory for Computer Assisted Writing and Translation" doc

... Subsentential Translation Memory for Computer Assisted Writing and Translation Jian-Cheng Wu Department of Computer Science National Tsing Hua University ... concordance designed as a computer assisted translation and language learning tool. Currently, TotalRecll uses Sinorama Magazine and HKLEGCO corpora as the databases of translation memory. We have ......

Ngày tải lên: 17/03/2014, 06:20

... Association for Computational Linguistics Partial Matching Strategy for Phrase-based Statistical Machine Translation Zhongjun He 1,2 and Qun Liu 1 and Shouxun Lin 1 1 Key Laboratory of Intelligent Information ... only found and used the semantically similar phrases. Another method is to use multi-parallel corpora (Cohn and Lapata, 2007; Utiyama and Isahara, 2007) to im- prove...

Ngày tải lên: 08/03/2014, 01:20

... morpho-syntactic information for translation between language pairs with scarce resources. Vandeghinste et al. (2006) used translation dic- tionaries and shallow analysis tools for translation between ... were also used for translation dictionary induction (Schafer and Yarowsky, 2002), word sense disam- biguation (Diab and Resnik, 2002), and so on. For the second...

Ngày tải lên: 08/03/2014, 02:21

... C. TRIAL TRANSLATION AND FORMULA FINDING The language of the logical calculus is simple and mnemonic, and appears to be well suited for the for- mulation of translation algorithms. A computer ... syntactic and semantic transformation T s that carries the word-by-word translation into a smooth and idio- matic translation. Although the output of this trans- formati...

Ngày tải lên: 16/03/2014, 19:20

... outperforms minimal rules, and performs at the same level as composed and vertically composed rules, but is smaller and faster. The number of parameters is shown for both the full model and the ... of D 1 and D 2 , the discount for bigrams and trigrams, respectively. Ney et al. (1994) suggest using the fol- lowing value for the discount D n : D n = n 1 n 1 + n 2 (4) 857 rule...

Ngày tải lên: 17/03/2014, 00:20

... 5-gram model. For GIZA ++, we use the standard training reg- imen up to Model 4, and combine alignments with grow-diag-final -and. For the proposed models, we train for 100 iterations, and use the ... use the news commentary corpus for training the TM, and the news commentary and Europarl corpora for training the LM. For Japanese, we use data from the NTCIR patent transla...

Ngày tải lên: 20/02/2014, 04:20

... Association for Computational Linguistics Integration of Speech to Computer- Assisted Translation Using Finite-State Automata Shahram Khadivi Richard Zens Lehrstuhl f ¨ ur Informatik 6 – Computer ... (Papineni et al., 1997; Papineni et al., 1998) for a natural language understanding task, by (Beyerlein, 1998) for an ASR task, and by (Och and Ney, 2002) for an MT task. This...

Ngày tải lên: 20/02/2014, 12:20

... Improved Parser for Data-Oriented Lexical-Functional Analysis Rens Bod Informatics Research Institute, University of Leeds, Leeds LS2 9JT, UK, & Institute for Logic, Language and Computation, ... frag- ment size is confirmed for LFG-DOP; (3) LFG- DOP's relative frequency estimator performs worse than a discounted frequency estimator; and (4) LFG-DOP significantly outperform...

Ngày tải lên: 20/02/2014, 18:20

... double- distilled water ( 2.5-fold of the pellet volume for keratino- cytes and DCs, and fivefold of the pellet volume for B cells) and centrifugation at 100 000 g for 5 min with a Beckman TL100 ultracentrifuge. ... different cell lines used for CatE and CatD determination For immunochemical determination of subcellular localization of CatE and CatD, western blot analysis...

Ngày tải lên: 07/03/2014, 09:20

... modeling pro- vides a formal and convenient way of grouping documents and words to topics. In order to apply topic models to our problem, we map RASCs to documents, items to words, and treat the output ... significantly fewer “documents”, “words”, and “topics”. To further improve efficiency, we also perform preprocess- ing (refer to Section 3.4 for details) before build- ing to...

Ngày tải lên: 08/03/2014, 00:20