Six Challenges for Neural Machine Translation

Philipp Koehn, Rebecca Knowles

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

Abstract

We explore six challenges for neural machine translation: domain mismatch, amount of training data, rare words, long sentences, word alignment, and beam search. We show both deficiencies and improvements over the quality of phrase-based statistical machine translation.
Original languageEnglish
Title of host publicationProceedings of the First Workshop on Neural Machine Translation
Place of PublicationVancouver, Canada
PublisherAssociation for Computational Linguistics
Pages28-39
Number of pages12
ISBN (Print)978-1-945626-68-5
DOIs
Publication statusPublished - 1 Aug 2017
EventFirst Workshop on Neural Machine Translation - Vancouver, Canada
Duration: 4 Aug 20174 Aug 2017
https://sites.google.com/site/acl17nmt/

Conference

ConferenceFirst Workshop on Neural Machine Translation
Abbreviated titleNMT 2017
Country/TerritoryCanada
CityVancouver
Period4/08/174/08/17
Internet address

Fingerprint

Dive into the research topics of 'Six Challenges for Neural Machine Translation'. Together they form a unique fingerprint.

Cite this