Paper: N-gram-based Tense Models for Statistical Machine Translation

ACL ID D12-1026
Title N-gram-based Tense Models for Statistical Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2012

Tense is a small element to a sentence, how- ever, error tense can raise odd grammars and result in misunderstanding. Recently, tense has drawn attention in many natural language processing applications. However, most of current Statistical Machine Translation (SMT) systems mainly depend on translation model and language model. They never consider and make full use of tense information. In this pa- per, we propose n-gram-based tense models for SMT and successfully integrate them in- to a state-of-the-art phrase-based SMT system via two additional features. Experimental re- sults on the NIST Chinese-English translation task show that our proposed tense models are very effective, contributing performance im- provement by 0.62 BLUE points over a strong baseline.