Semantic smoothing and fabrication of phrase pairs for SMT

  1. (PDF, 425 KB)
AuthorSearch for: ; Search for: ; Search for:
Proceedings titleProceedings of the International Workshop on Spoken Lanuage Translation (IWSLT-2011)
ConferenceInternational Workshop on Spoken Language Translation (IWSLT) 2011, December 8-9, 2011, San Francisco, California
AbstractIn statistical machine translation systems, phrases with similar meanings often have similar but not identical distributions of translations. This paper proposes a new soft clustering method to smooth the conditional translation probabilities for a given phrase with those of semantically similar phrases. We call this semantic smoothing (SS). Moreover, we fabricate new phrase pairs that were not observed in training data, but which may be used for decoding. In learning curve experiments against a strong baseline, we obtain a consistent pattern of modest improvement from semantic smoothing, and further modest improvement from phrase pair fabrication.
Publication date
AffiliationNRC Institute for Information Technology; National Research Council Canada
Peer reviewedYes
NPARC number19649698
Export citationExport as RIS
Report a correctionReport a correction
Record identifiere86752cf-7b89-4f65-baa1-8a31a9d762b6
Record created2012-03-20
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)