Going beyond AER: an extensive analysis of word alignments and their impact on MT

TitleGoing beyond AER: an extensive analysis of word alignments and their impact on MT
Publication TypeConference Papers
Year of Publication2006
AuthorsAyan N F, Dorr BJ
Conference NameProceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Date Published2006///
PublisherAssociation for Computational Linguistics
Conference LocationStroudsburg, PA, USA
Abstract

This paper presents an extensive evaluation of five different alignments and investigates their impact on the corresponding MT system output. We introduce new measures for intrinsic evaluations and examine the distribution of phrases and untranslated words during decoding to identify which characteristics of different alignments affect translation. We show that precision-oriented alignments yield better MT output (translating more words and using longer phrases) than recall-oriented alignments.

URLhttp://dx.doi.org/10.3115/1220175.1220177
DOI10.3115/1220175.1220177