Paper: Word Sense Disambiguation Vs. Statistical Machine Translation

ACL ID P05-1048
Title Word Sense Disambiguation Vs. Statistical Machine Translation
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2005
Authors

We directly investigate a subject of much recent debate: do word sense disambiga- tion models help statistical machine trans- lation quality? We present empirical re- sults casting doubt on this common, but unproved, assumption. Using a state-of- the-art Chinese word sense disambigua- tion model to choose translation candi- dates for a typical IBM statistical MT system, we find that word sense disam- biguation does not yield significantly bet- ter translation quality than the statistical machine translation system alone. Error analysis suggests several key factors be- hind this surprising finding, including in- herent limitations of current statistical MT architectures.