liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
German Compounds in Factored Statistical Machine Translation
Linköping University, The Institute of Technology. Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory.
2008 (English)In: -, Berlin, Germany: Springer , 2008, 464-475 p.Conference paper (Refereed)
Abstract [en]

An empirical method for splitting German compounds is explored by varying it in a number of ways to investigate the consequences for factored statistical machine translation between English and German in both directions. Compound splitting is incorporated into translation in a preprocessing step, performed on training data and on German translation input. For translation into German, compounds are merged based on part-of-speech in a postprocessing step. Compound parts are marked, to separate them from ordinary words. Translation quality is improved in both translation directions and the number of untranslated words in the English output is reduced. Different versions of the splitting algorithm performs best in the two different translation directions.

Place, publisher, year, edition, pages
Berlin, Germany: Springer , 2008. 464-475 p.
Keyword [en]
machine translation, compounds
National Category
Computer Science
URN: urn:nbn:se:liu:diva-44110DOI: 10.1007/978-3-540-85287-2_44Local ID: 75561OAI: diva2:264971
6th International Conference on Natural Language Processing GoTAL, 2008
Available from: 2009-10-10 Created: 2009-10-10 Last updated: 2009-12-07Bibliographically approved
In thesis
1. Compound Processing for Phrase-Based Statistical Machine Translation
Open this publication in new window or tab >>Compound Processing for Phrase-Based Statistical Machine Translation
2009 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

In this thesis I explore how compound processing can be used to improve phrase-based statistical machine translation (PBSMT) between English and German/Swedish. Both German and Swedish generally use closed compounds, which are written as one word without spaces or other indicators of word boundaries. Compounding is both common and productive, which makes it problematic for PBSMT, mainly due to sparse data problems.

The adopted strategy for compound processing is to split compounds into their component parts before training and translation. For translation into Swedish and German the parts are merged after translation. I investigate the effect of different splitting algorithms for translation between English and German, and of different merging algorithms for German. I also apply these methods to a different language pair, English--Swedish. Overall the studies show that compound processing is useful, especially for translation from English into German or Swedish. But there are improvements for translation into English as well, such as a reduction of unknown words.

I show that for translation between English and German different splitting algorithms work best for different translation directions. I also design and evaluate a novel merging algorithm based on part-of-speech matching, which outperforms previous methods for compound merging, showing the need for information that is carried through the translation process, rather than only external knowledge sources such as word lists. Most of the methods for compound processing were originally developed for German. I show that these methods can be applied to Swedish as well, with similar results.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2009. 64 p.
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 1421
Machine translation, compounds, factored translation, statistical machine translation, computational linguistics
National Category
Language Technology (Computational Linguistics) Language Technology (Computational Linguistics) Computer Science
urn:nbn:se:liu:diva-51416 (URN)978-91-7393-501-2 (ISBN)
2009-12-18, Alan Turing, Hus E, Campus Valla, Linköpings universitet, Linköping, 13:15 (English)
Available from: 2009-12-07 Created: 2009-10-30 Last updated: 2009-12-07Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textLink to Licentiate Thesis

Search in DiVA

By author/editor
Stymne, Sara
By organisation
The Institute of TechnologyNLPLAB - Natural Language Processing Laboratory
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 42 hits
ReferencesLink to record
Permanent link

Direct link