Compound Merging Strategies for Statistical Machine Translation
2010 (English)In: Grace Hopper Celebration of Women in Computing, 2010, 43-43 p.Conference paper (Other academic)
Translation into compounding languages like German and Swedish is a challenge for statistical machine translation. I present a novel algorithm for merging compound parts, based on part-of-speech matching with an extended tag set. It improves the quality of merged compounds compared to previously suggested methods, both measured automatically and shown in an error analysis. Translation is also improved compared to systems without compound processing for Swedish, Danish, and German.
Place, publisher, year, edition, pages
2010. 43-43 p.
Statistical machine translation, compounds, Germanic languages
National CategoryComputer Science Language Technology (Computational Linguistics) Language Technology (Computational Linguistics)
IdentifiersURN: urn:nbn:se:liu:diva-63351OAI: oai:DiVA.org:liu-63351DiVA: diva2:378799
Grace Hopper Celebration of Women in Computing