Investigating the usefulness of generalizedword representations in SMT

Nadir Durrani, Philipp Koehn, Helmut Schmid, Alexander Fraser

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

19 Citations (Scopus)

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 COLING 2014
Subtitle of host publicationTechnical Papers
PublisherAssociation for Computational Linguistics, ACL Anthology
Pages421-432
Number of pages12
ISBN (Electronic)9781941643266
Publication statusPublished - 2014
Externally publishedYes
Event25th International Conference on Computational Linguistics, COLING 2014 - Dublin, Ireland
Duration: 23 Aug 201429 Aug 2014

Publication series

NameCOLING 2014 - 25th International Conference on Computational Linguistics, Proceedings of COLING 2014: Technical Papers

Conference

Conference25th International Conference on Computational Linguistics, COLING 2014
Country/TerritoryIreland
CityDublin
Period23/08/1429/08/14

Fingerprint

Dive into the research topics of 'Investigating the usefulness of generalizedword representations in SMT'. Together they form a unique fingerprint.

Cite this