Investigating the Usefulness of Generalized Word Representations in SMT

Nadir Durrani, Philipp Koehn, Helmut Schmid, Alexander M. Fraser

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We investigate the use of generalized representations (POS, morphological analysis and word clusters) in phrase-based models and the N-gram-based Operation Sequence Model (OSM). Our integration enables these models to learn richer lexical and reordering patterns, consider wider contextual information and generalize better in sparse data conditions. When interpolating generalized OSM models on the standard IWSLT and WMT tasks we observed improvements of up to +1.35 on the English-to-German task and +0.63 for the German-to-English task. Using automatically generated word classes in standard phrase-based models and the OSM models yields an average improvement of +0.80 across 8 language pairs on the IWSLT shared task.
Original languageEnglish
Title of host publicationCOLING 2014, 25th International Conference on Computational Linguistics, Proceedings of the Conference: Technical Papers, August 23-29, 2014, Dublin, Ireland
Pages421-432
Number of pages12
Publication statusPublished - Aug 2014

Fingerprint Dive into the research topics of 'Investigating the Usefulness of Generalized Word Representations in SMT'. Together they form a unique fingerprint.

Cite this