Alignment link projection using transformation-based learning

TitleAlignment link projection using transformation-based learning
Publication TypeConference Papers
Year of Publication2005
AuthorsAyan N F, Dorr BJ, Monz C
Conference NameProceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Date Published2005///
PublisherAssociation for Computational Linguistics
Conference LocationStroudsburg, PA, USA
Abstract

We present a new word-alignment approach that learns errors made by existing word alignment systems and corrects them. By adapting transformation-based learning to the problem of word alignment, we project new alignment links from already existing links, using features such as POS tags. We show that our alignment link projection approach yields a significantly lower alignment error rate than that of the best performing alignment system (22.6% relative reduction on English-Spanish data and 23.2% relative reduction on English-Chinese data).

URLhttp://dx.doi.org/10.3115/1220575.1220599
DOI10.3115/1220575.1220599