Zero-resource translation with multi-lingual neural machine translation

Orhan Firat, Baskaran Sankaran, Yaser Al-Onaizan, Fatos T. Yarman Vural, Kyunghyun Cho

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

Abstract

In this paper, we propose a novel finetuning algorithm for the recently introduced multi-way, multilingual neural machine translate that enables zero-resource machine translation. When used together with novel many-to-one translation strategies, we empirically show that this finetuning algorithm allows the multi-way, multilingual model to translate a zero-resource language pair (1) as well as a single-pair neural translation model trained with up to 1M direct parallel sentences of the same language pair and (2) better than pivot-based translation strategy, while keeping only one additional copy of attention-related parameters.

Original languageEnglish (US)
Title of host publicationEMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages268-277
Number of pages10
ISBN (Electronic)9781945626258
StatePublished - Jan 1 2016
Event2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 - Austin, United States
Duration: Nov 1 2016Nov 5 2016

Publication series

NameEMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016
CountryUnited States
CityAustin
Period11/1/1611/5/16

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Cite this