uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
Estimating Word Alignment Quality for SMT Reordering Tasks
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Languages, Department of Linguistics and Philology. (Datorlingvistik)
2014 (English)In: Proceedings of the Ninth Workshop on Statistical Machine Translation, 2014, 275-286 p.Conference paper (Refereed)
Abstract [en]

Previous studies of the effect of word alignment on translation quality in SMT generally explore link level metrics only and mostly do not show any clear connections between alignment and SMT quality. In this paper, we specifically investigate the impact of word alignment on two pre-reordering tasks in translation, using a wider range of quality indicators than previously done. Experiments on German–English translation show that reordering may require alignment models different from those used by the core translation system. Sparse alignments with high precision on the link level, for translation units, and on the subset of crossing links, like intersected HMM models, are preferred. Unlike SMT performance the desired alignment characteristics are similar for small and large training data for the pre-reordering tasks. Moreover, we confirm previous research showing that the fuzzy reordering score is a useful and cheap proxy for performance on SMT reordering tasks.

Place, publisher, year, edition, pages
2014. 275-286 p.
National Category
Language Technology (Computational Linguistics)
Research subject
Computational Linguistics
URN: urn:nbn:se:uu:diva-240113OAI: oai:DiVA.org:uu-240113DiVA: diva2:775941
Ninth Workshop on Statistical Machine Translation
eSSENCE - An eScience Collaboration
Available from: 2015-01-05 Created: 2015-01-05 Last updated: 2016-02-18

Open Access in DiVA

No full text

Other links


Search in DiVA

By author/editor
Stymne, SaraNivre, Joakim
By organisation
Department of Linguistics and Philology
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar

Total: 155 hits
ReferencesLink to record
Permanent link

Direct link