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

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Alignment-based reordering for SMT
Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory. Linköping University, The Institute of Technology.
Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory. Linköping University, The Institute of Technology.
Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory. Linköping University, The Institute of Technology.
Linköping University, Department of Computer and Information Science, NLPLAB - Natural Language Processing Laboratory. Linköping University, The Institute of Technology.
2012 (English)In: Proceedings of the Eight International Conference on Language Resources and Evaluation (LREC'12), 2012, 3436-3440 p.Conference paper, Published paper (Other academic)
Abstract [en]

We present a method for improving word alignment quality for phrase-based statistical machine translation by reordering the source text according to the target word order suggested by an initial word alignment. The reordered text is used to create a second word alignment which can be an improvement of the first alignment, since the word order is more similar. The method requires no other pre-processing such as part-of-speech tagging or parsing. We report improved Bleu scores for English-to-German and English-to-Swedish translation. We also examined the effect on word alignment quality and found that the reordering method increased recall while lowering precision, which partly can explain the improved Bleu scores. A manual evaluation of the translation output was also performed to understand what effect our reordering method has on the translation system. We found that where the system employing reordering differed from the baseline in terms of having more words, or a different word order, this generally led to an improvement in translation quality.

Place, publisher, year, edition, pages
2012. 3436-3440 p.
Keyword [en]
Mahine translation, statistical machine translation, word alignment, reordering
National Category
Language Technology (Computational Linguistics)
Identifiers
URN: urn:nbn:se:liu:diva-80355OAI: oai:DiVA.org:liu-80355DiVA: diva2:546568
Conference
The Eight International Conference on Language Resources and Evaluation (LREC'12), May 2012, Istanbul, Turkey
Available from: 2012-08-23 Created: 2012-08-23 Last updated: 2012-09-03

Open Access in DiVA

No full text

Other links

http://www.lrec-conf.org/proceedings/lrec2012/pdf/1000_Paper.pdf

Authority records BETA

Holmqvist, MariaStymne, SaraAhrenberg, LarsMerkel, Magnus

Search in DiVA

By author/editor
Holmqvist, MariaStymne, SaraAhrenberg, LarsMerkel, Magnus
By organisation
NLPLAB - Natural Language Processing LaboratoryThe Institute of Technology
Language Technology (Computational Linguistics)

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 71 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf