Passive and pervasive use of a bilingual dictionary in statistical machine translation
Josef van Genabith
Date of Issue2015
Proceedings of the ACL 2015 Fourth Workshop on Hybrid Approaches to Translation
School of Humanities and Social Sciences
There are two primary approaches to the use bilingual dictionary in statistical machine translation: (i) the passive approach of appending the parallel training data with a bilingual dictionary and (ii) the pervasive approach of enforcing translation as per the dictionary entries when decoding. Previous studies have shown that both approaches provide external lexical knowledge to statistical machine translation thus improving translation quality. We empirically investigate the effects of both approaches on the same dataset and provide further insights on how lexical information can be reinforced in statistical machine translation.
Linguistics and Multilingual Studies
© 2015 Association for Computational Linguistics (ACL). This paper was published in Proceedings of the ACL 2015 Fourth Workshop on Hybrid Approaches to Translation and is made available as an electronic reprint (preprint) with permission of Association for Computational Linguistics (ACL). The published version is available at: [http://glicom.upf.edu/hytra2015/pdf/HyTra-405.pdf]. One print or electronic copy may be made for personal use only. Systematic or multiple reproduction, distribution to multiple locations via electronic or other means, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper is prohibited and is subject to penalties under law.