Modelling Pronominal Anaphora in Statistical Machine Translation

Christian Hardmeier, Marcello Federico

Research output: Contribution to conferencePaperpeer-review

Abstract / Description of output

Current Statistical Machine Translation (SMT) systems translate texts sentence by sentence without considering any cross-sentential context. Assuming independence between sentences makes it difficult to take certain translation decisions when the necessary information cannot be determined locally. We argue for the necessity to include cross-sentence dependencies in SMT. As a case in point, we study the problem of pronominal anaphora translation by manually evaluating German-English SMT output. We then present a word dependency model for SMT, which can represent links between word pairs in the same or in different sentences. We use this model to integrate the output of a coreference resolution system into English-German SMT with a view to improving the translation of anaphoric pronouns.
Original languageEnglish
Pages283-289
Number of pages7
Publication statusPublished - 3 Dec 2010
Event7th International Workshop on Spoken Language Translation - Paris, France
Duration: 2 Dec 20103 Dec 2010
http://iwslt2010.fbk.eu/

Workshop

Workshop7th International Workshop on Spoken Language Translation
Abbreviated titleIWSLT 2010
Country/TerritoryFrance
CityParis
Period2/12/103/12/10
Internet address

Fingerprint

Dive into the research topics of 'Modelling Pronominal Anaphora in Statistical Machine Translation'. Together they form a unique fingerprint.

Cite this