Document-Wide Decoding for Phrase-Based Statistical Machine Translation

Christian Hardmeier, Joakim Nivre, Jörg Tiedemann

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

Abstract

Independence between sentences is an assumption deeply entrenched in the models and algorithms used for statistical machine translation (SMT), particularly in the popular dynamic programming beam search decoding algorithm. This restriction is an obstacle to research on more sophisticated discourse-level models for SMT. We propose a stochastic local search decoding method for phrase-based SMT, which permits free document-wide dependencies in the models. We explore the stability and the search parameters of this method and demonstrate that it can be successfully used to optimise a document-level semantic language model.
Original languageEnglish
Title of host publicationProceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Place of PublicationJeju Island, Korea
PublisherAssociation for Computational Linguistics
Pages1179-1190
Number of pages12
ISBN (Electronic)978-1-937284-43-5
Publication statusPublished - 14 Jul 2012
Event2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Jeju Island, Korea, Republic of
Duration: 12 Jul 201214 Jul 2012
http://emnlp-conll2012.unige.ch/

Conference

Conference2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012
CountryKorea, Republic of
CityJeju Island
Period12/07/1214/07/12
Internet address

Fingerprint Dive into the research topics of 'Document-Wide Decoding for Phrase-Based Statistical Machine Translation'. Together they form a unique fingerprint.

Cite this