Vs and OOVs: Two Problems for Translation between German and English
2010 (English)In: Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR (WMT'10), 2010, 183-188 p.Conference paper (Refereed)
In this paper we report on experiments with three preprocessing strategies for improving translation output in a statistical MT system. In training, two reordering strategies were studied: (i) reorder on thebasis of the alignments from Giza++, and (ii) reorder by moving all verbs to the end of segments. In translation, out-of-vocabulary words were preprocessed in a knowledge-lite fashion to identify a likely equivalent. All three strategies were implemented for our English-German systems submitted to the WMT10 shared task. Combining them lead to improvements in both language directions.
Place, publisher, year, edition, pages
2010. 183-188 p.
Machine translation, reordering, Out-of-vocabulary words
Language Technology (Computational Linguistics) Computer Science
IdentifiersURN: urn:nbn:se:liu:diva-58979ISBN: 978-1-932432-71-8ISBN: 1-932432-71-XOAI: oai:DiVA.org:liu-58979DiVA: diva2:347920
The Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR, 15-16 July 2010