Paper: Source-Language Entailment Modeling for Translating Unknown Terms

ACL ID P09-1089
Title Source-Language Entailment Modeling for Translating Unknown Terms
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2009
Authors

This paper addresses the task of handling unknown terms in SMT. We propose us- ing source-language monolingual models and resources to paraphrase the source text prior to translation. We further present a conceptual extension to prior work by al- lowing translations of entailed texts rather than paraphrases only. A method for performing this process efficiently is pre- sented and applied to some 2500 sentences with unknown terms. Our experiments show that the proposed approach substan- tially increases the number of properly translated texts.