Paper: Improving Translation Quality by Discarding Most of the Phrasetable

ACL ID D07-1103
Title Improving Translation Quality by Discarding Most of the Phrasetable
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2007
Authors

It is possible to reduce the bulk of phrase- tablesforStatisticalMachineTranslationus- ing a technique based on the significance testing of phrase pair co-occurrence in the parallel corpus. The savings can be quite substantial (up to 90%) and cause no reduc- tion in BLEU score. In some cases, an im- provement in BLEU is obtained at the same time although the effect is less pronounced if state-of-the-art phrasetable smoothing is employed.