Dynamic Topic Adaptation for Phrase-based MT

Eva Hasler, Phil Blunsom, Philipp Koehn, Barry Haddow

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Translating text from diverse sources poses a challenge to current machine translation systems which are rarely adapted to structure beyond corpus level. We explore topic adaptation on a diverse data set and present a new bilingual variant of Latent Dirichlet Allocation to compute topic-adapted, probabilistic phrase translation features. We dynamically infer document-specific translation probabilities for test sets of unknown origin, thereby capturing the effects of document context on phrase translations. We show gains of up to 1.26 BLEU over the baseline and 1.04 over a domain adaptation benchmark. We further provide an analysis of the domain-specific data and show additive gains of our model in combination with other types of topic-adapted features.
Original languageEnglish
Title of host publicationProceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014, April 26-30, 2014, Gothenburg, Sweden
Place of PublicationGothenburg, Sweden
PublisherAssociation for Computational Linguistics (ACL)
Pages328-337
Number of pages10
DOIs
Publication statusPublished - Apr 2014
Event14th Conference of the European Chapter of the Association for Computational Linguistics - Chalmers University, Gothenburg, Sweden
Duration: 26 Apr 201430 Apr 2014
http://eacl2014.org/

Conference

Conference14th Conference of the European Chapter of the Association for Computational Linguistics
Abbreviated titleEACL 2014
Country/TerritorySweden
CityGothenburg
Period26/04/1430/04/14
Internet address

Fingerprint

Dive into the research topics of 'Dynamic Topic Adaptation for Phrase-based MT'. Together they form a unique fingerprint.

Cite this