A purely monotonic approach to machine translation for similar languages

Ye Kyaw Thu, Andrew Finch, Eiichiro Sumita, Yoshinori Sagisaka

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

Abstract

This paper investigates the effect of taking a strictly monotonic approach to machine translation for a restricted set of suitable language pairs. We studied the effect of decoding monotonically for a set of language pairs which has similar word order characteristics and found that for some language pairs - namely language pairs where both languages are in SOV order - there was almost no difference in machine translation quality. The results of this experiment motivated the extension of the monotonic approach into the alignment stage of the training. We used a Bayesian non-parametric aligner that has been shown to out-perform GIZA++ in combination with the grow-diag-final- and heuristic on transliteration data. Our results show that the monotonic aligner was able to match the performance of the GIZA++ baseline, and gains in translation performance were obtained by integrating both aligners into the systems.

Original languageEnglish
Title of host publicationProceedings - 2013 International Conference on Asian Language Processing, IALP 2013
Pages107-110
Number of pages4
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 International Conference on Asian Language Processing, IALP 2013 - Urumqi, Xinjiang, China
Duration: 2013 Aug 172013 Aug 19

Publication series

NameProceedings - 2013 International Conference on Asian Language Processing, IALP 2013

Conference

Conference2013 International Conference on Asian Language Processing, IALP 2013
Country/TerritoryChina
CityUrumqi, Xinjiang
Period13/8/1713/8/19

Keywords

  • bilingual alignment
  • machine translation
  • monotonic decoding

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'A purely monotonic approach to machine translation for similar languages'. Together they form a unique fingerprint.

Cite this