Philip Resnik and I. Dan Melamed. 1997. "Semi-Automatic Acquisition of DomainSpecific Translation Lexicons" in Proceedings of the 5th ANLP Conference.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....lexicon entries with 99 precision and 46 recall when trained on 13 million words of the Hansard corpus, where recall was measured as the fraction of words from the bitext that were assigned some translation. Using the same model but less data, a French English software manual of 400,000 words, Resnik and Melamed (1997) reported 94 precision with 30 recall. While these figures are indeed impressive, more telling figures can only be obtained by measuring the effect of the alignment system on some specific task. Dagan and Church (1994) reports that their Termight system helped double the speed at which ....

Resnik, P. & I. D. Melamed. (1997) "Semi-Automatic Acquisition of Domain-Specific Translation Lexicons." In Proceedings of the 7th ACL Conference on Applied Natural Language Processing. Washington DC.

....different entries for that key are ranked. Finally, the MLB files are automatically processed to generate a fast loadable version of the transfer rules. SABLE is a tool for analyzing bilingual corpora (or bitexts ) Melamed, July 1997) SABLE can induce domain specific bilingual transfer lexicons (Resnik and Melamed, 1997) using a fast algorithm for estimating a partial translation model. A translation model is a set of transfer pairs, consisting of one word from each language which are (in some context in the bitext) a translation of one another. The model s accuracy coverage trade off can be directly controlled ....

Resnik, P. and Melamed, I. D. (1997). Semi-Automatic Acquisition of Domain-Specific Translation Lexicons. In Proceedings of the ANLP-97, Washington, D.C.

....yield a multi way parallel corpus with representation from every language family, with the content carefully translated and nearly sentence level alignment included. Although it is not the largest of corpora, parallel corpora of significantly smaller size have yielded useful results, e.g. (Resnik and Melamed, 1997), and although its content is more specialized than, say, contemporary newspaper text, it does cover a very wide range of linguistic phenomena and domains of world knowledge; for example, see the range of conceptual categories in the Louw Nida thesaurus for the New Testament (Louw and Nida, ....

Resnik, Philip and I. Dan Melamed. 1997. Semi-automatic acquisition of domain-specific translation lexicons. In Fifth Conference on Applied Natural Language Processing, Washington, D.C.

.... Littman, 1990; also see Oard, 1997) However, for all but relatively few language pairs, parallel corpora are available only in relatively specialized forms such as United Nations proceedings (LDC, 1996) religious texts (Resnik, Olsen, and Diab, 1998) and localized versions of software manuals (Resnik and Melamed, 1997). Even for the top dozen or so majority languages, the available parallel corpora tend to be unbalanced, representing primarily governmental and newswire style texts. In addition, like other language resources, parallel corpora are often encumbered by fees or licensing restrictions. For all these ....

Resnik, P., & Melamed, I. D. (1997). Semi-automatic acquisition of domain-specific translation lexicons. In Fifth Conference on Applied Natural Language Processing, Washington, D.C.

No context found.

P. Resnik & I. D. Melamed, "Semi-Automatic Acquisition of Domain-Specific Translation Lexicons," Proceedings of the Conference on Applied Natural Language Processing, Washington, D.C., 1997.

....1991; Melamed, 1996a) Then, two word tokens (u; v) are said to co occur in the aligned segment pair i if u 2 S i and v 2 T i . The co occurrence relation can also be based on distance in a bitext space, which is a more general representations of bitext correspondence (Dagan et al. 1993; Resnik Melamed, 1997), or it can be restricted to words pairs that satisfy some matching predicate, which can be extrinsic to the model (Melamed, 1995; Melamed, 1997) 3 The Basic Word to Word Model Our translation model consists of the hidden parameters and Gamma , and likelihood ratios L(u; v) The two ....

....criterion carries much practical import, because many of the applications mentioned in Section 1 depend on accurate broad coverage translation lexicons. Machine readable bilingual dictionaries, even when they are available, have only limited coverage and rarely include domain specific terms (Resnik Melamed, 1997). We define the recall of a word to word translation model as the fraction of the bitext vocabulary represented in the model. Translation model precision is a more thorny issue, because people disagree about the degree to which context should play a role in judgements of translational equivalence. ....

[Article contains additional citation context not shown here]

P. Resnik & I. D. Melamed, "Semi-Automatic Acquisition of Domain-Specific Translation Lexicons," Proceedings of the 7th ACL Conference on Applied Natural Language Processing, Washington, DC, 1997.

No context found.

Philip Resnik and I. Dan Melamed. 1997. "Semi-Automatic Acquisition of DomainSpecific Translation Lexicons" in Proceedings of the 5th ANLP Conference.

No context found.

Philip Resnik and I. Dan Melamed. 1997. "Semi-Automatic Acquisition of DomainSpecific Translation Lexicons" in Proceedings of the 5th ANLP Conference. 11

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC