Phrase table pruning via submodular function maximization

Masaaki Nishino, Jun Suzuki, Masaaki Nagata

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

Abstract

Phrase table pruning is the act of removing phrase pairs from a phrase table to make it smaller, ideally removing the least useful phrases first. We propose a phrase table pruning method that formulates the task as a submodular function maximization problem, and solves it by using a greedy heuristic algorithm. The proposed method can scale with input size and long phrases, and experiments show that it achieves higher BLEU scores than state-of-the-art pruning methods.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages406-411
Number of pages6
ISBN (Electronic)9781510827592
DOIs
Publication statusPublished - 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: 2016 Aug 72016 Aug 12

Publication series

Name54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period16/8/716/8/12

ASJC Scopus subject areas

  • Language and Linguistics
  • Artificial Intelligence
  • Linguistics and Language
  • Software

Fingerprint Dive into the research topics of 'Phrase table pruning via submodular function maximization'. Together they form a unique fingerprint.

Cite this