Four techniques for online handling of out-of-vocabulary words in Arabic-English statistical machine translation

Research output: Contribution to journalConference articlepeer-review

Abstract

We present four techniques for online handling of Out-of-Vocabulary words in Phrase-based Statistical Machine Translation. The techniques use spelling expansion, morphological expansion, dictionary term expansion and proper name transliteration to reuse or extend a phrase table. We compare the performance of these techniques and combine them. Our results show a consistent improvement over a state-of-the-art baseline in terms of BLEU and a manual error analysis.

Original languageEnglish (US)
Pages (from-to)57-60
Number of pages4
JournalProceedings of the Annual Meeting of the Association for Computational Linguistics
DOIs
StatePublished - 2008
Event46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL 2008 - Columbus, United States
Duration: Jun 16 2008Jun 17 2008

ASJC Scopus subject areas

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics

Fingerprint

Dive into the research topics of 'Four techniques for online handling of out-of-vocabulary words in Arabic-English statistical machine translation'. Together they form a unique fingerprint.

Cite this