Dynamic Topic Adaptation for SMT using Distributional Profiles

Eva Hasler, Barry Haddow, Philipp Koehn

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

Abstract / Description of output

Despite its potential to improve lexical selection, most state-of-the-art machine translation systems take only minimal contextual information into account. We capture context with a topic model over distributional profiles built from the context words of each translation unit. Topic distributions are inferred for each translation unit and used to adapt the translation model dynamically to a given test context by measuring their similarity. We show that combining information from both local and global test contexts helps to improve lexical selection and outperforms a baseline system by up to 1.15 B LEU. We test our topic-adapted model on a diverse data set containing documents from three different domains and achieve competitive performance in comparison with two supervised domain-adapted systems.
Original languageEnglish
Title of host publicationProceedings of the Ninth Workshop on Statistical Machine Translation
Place of PublicationBaltimore, Maryland, USA
PublisherAssociation for Computational Linguistics
Number of pages12
Publication statusPublished - 1 Jun 2014
EventNinth Workshop on Statistical Machine Translation - Baltimore, United States
Duration: 26 Jun 201427 Jun 2014


ConferenceNinth Workshop on Statistical Machine Translation
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'Dynamic Topic Adaptation for SMT using Distributional Profiles'. Together they form a unique fingerprint.

Cite this