Alignment symmetrization optimization targeting phrase pivot statistical machine translation

Ahmed El Kholy, Nizar Habash

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

Abstract

An important step in mainstream statistical machine translation (SMT) is combining bidirectional alignments into one alignment model. This process is called symmetrization. Most of the symmetrization heuristics and models are focused on direct translation (source-to-target). In this paper, we present symmetrization heuristic relaxation to improve the quality of phrase-pivot SMT (source-[pivot]-target). We show positive results (1.2 BLEU points) on Hebrew-to-Arabic SMT pivoting on English.

Original languageEnglish (US)
Title of host publicationProceedings of the 17th Annual Conference of the European Association for Machine Translation, EAMT 2014
EditorsMarko Tadic, Philipp Koehn, Philipp Koehn, Andy Way, Johann Roturier
PublisherEuropean Association for Machine Translation
Pages63-70
Number of pages8
ISBN (Electronic)9789535537533
StatePublished - 2014
Event17th Annual Conference of the European Association for Machine Translation, EAMT 2014 - Dubrovnik, Croatia
Duration: Jun 16 2014Jun 18 2014

Publication series

NameProceedings of the 17th Annual Conference of the European Association for Machine Translation, EAMT 2014

Other

Other17th Annual Conference of the European Association for Machine Translation, EAMT 2014
Country/TerritoryCroatia
CityDubrovnik
Period6/16/146/18/14

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Software

Fingerprint

Dive into the research topics of 'Alignment symmetrization optimization targeting phrase pivot statistical machine translation'. Together they form a unique fingerprint.

Cite this