Paper: A Class-Based Agreement Model for Generating Accurately Inflected Translations

ACL ID P12-1016
Title A Class-Based Agreement Model for Generating Accurately Inflected Translations
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

When automatically translating from a weakly inflected source language like English to a tar- get language with richer grammatical features such as gender and dual number, the output commonly contains morpho-syntactic agree- ment errors. To address this issue, we present a target-side, class-based agreement model. Agreement is promoted by scoring a sequence of fine-grained morpho-syntactic classes that are predicted during decoding for each transla- tion hypothesis. For English-to-Arabic transla- tion, our model yields a +1.04 BLEU average improvement over a state-of-the-art baseline. The model does not require bitext or phrase ta- ble annotations and can be easily implemented as a feature in many phrase-based decoders.