Paper: Search-Aware Tuning for Machine Translation

ACL ID D14-1209
Title Search-Aware Tuning for Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014

Parameter tuning is an important problem in statistical machine translation, but surpris- ingly, most existing methods such as MERT, MIRA and PRO are agnostic about search, while search errors could severely degrade translation quality. We propose a search- aware framework to promote promising par- tial translations, preventing them from be- ing pruned. To do so we develop two met- rics to evaluate partial derivations. Our tech- nique can be applied to all of the three above-mentioned tuning methods, and ex- tensive experiments on Chinese-to-English and English-to-Chinese translation show up to +2.6 BLEU gains over search-agnostic baselines.