论文信息 - Evaluation of Eurowordnet- and LCS- based lexical resources for machine translation

Evaluation of Eurowordnet- and LCS- based lexical resources for machine translation

We evaluate two types of lexical resources with respect to their applicability to interlingual machine translation: (1) a EuroWordNetbased database of bilingual links between Spanish and English words; and (2) a repository of semantically classified verbs with their corresponding Lexical Conceptual Structure (LCS) representations. We examine the utility of these two resources for the task of lexical selection in machine translation. Our approach uses a coarse-grained graph-matching scheme that selects target-language words based on their LCS representation. The final selection of target-language terms is based on a finer-grained linking into the EuroWordNet-based repository.

[1] Bonnie J. Dorr,et al. Large-Scale Acquisition of LCS-Based Lexicons for Foreign Language Tutoring , 1997, ANLP.

[2] Beth Levin,et al. English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[3] L. Talmy. Lexicalisation patterns: semantic structure in lexical forms , 1985 .

[4] Bonnie J. Dorr,et al. Role of Word Sense Disalnbiguation in Lexical Acquisition: Predicting Semantics from Syntactic Cues , 1996, COLING.

[5] George A. Miller,et al. Introduction to WordNet: An On-line Lexical Database , 1990 .

[6] Leonard Talmy,et al. (1) Lexicalization patterns: Semantic structure in lexical forms; and , 1987 .

[7] S. Pinker. Learnability and Cognition: The Acquisition of Argument Structure , 1989 .

[8] Bonnie J. Dorr,et al. Spanish EuroWordNet and LCS-based interlingual MT , 1997, MTSUMMIT.

[9] George A. Miller,et al. Dictionaries of the Mind , 1985, ACL.

[10] G. Miller,et al. Semantic networks of english , 1991, Cognition.

[11] Philip Resnik,et al. Using Information Content to Evaluate Semantic Similarity in a Taxonomy , 1995, IJCAI.