Word alignment with stochastic bracketing linear inversion transduction grammar

Markus Saers*, Joakim Nivre, Dekai Wu

*Corresponding author for this work

Research output: Chapter in Book/Conference Proceeding/ReportConference Paper published in a bookpeer-review

19 Citations (Scopus)

Abstract

The class of Linear Inversion Transduction Grammars (LITGs) is introduced, and used to induce a word alignment over a parallel corpus. We show that alignment via Stochastic Bracketing LITGs is considerably faster than Stochastic Bracketing ITGs, while still yielding alignments superior to the widely-used heuristic of intersecting bidirectional IBM alignments. Performance is measured as the translation quality of a phrase-based machine translation system built upon the word alignments, and an improvement of 2.85 BLEU points over baseline is noted for French-English.

Original languageEnglish
Title of host publicationNAACL HLT 2010 - Human Language Technologies
Subtitle of host publicationThe 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference
Pages341-344
Number of pages4
Publication statusPublished - 2010
Event2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010 - Los Angeles, CA, United States
Duration: 2 Jun 20104 Jun 2010

Publication series

NameNAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference

Conference

Conference2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010
Country/TerritoryUnited States
CityLos Angeles, CA
Period2/06/104/06/10

Fingerprint

Dive into the research topics of 'Word alignment with stochastic bracketing linear inversion transduction grammar'. Together they form a unique fingerprint.

Cite this