On the properties of neural machine translation: Encoder–decoder approaches

Kyunghyun Cho, Bart van Merriënboer, Dzmitry Bahdanau, Yoshua Bengio

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

Abstract

Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder–Decoder and a newly proposed gated recursive convolutional neural network. We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase. Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence automatically.

Original languageEnglish (US)
Title of host publicationProceedings of SSST 2014 - 8th Workshop on Syntax, Semantics and Structure in Statistical Translation
EditorsDekai Wu, Marine Carpuat, Xavier Carreras, Eva Maria Vecchi
PublisherAssociation for Computational Linguistics (ACL)
Pages103-111
Number of pages9
ISBN (Electronic)9781937284961
StatePublished - 2014
Event8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2014 - Doha, Qatar
Duration: Oct 25 2014 → …

Publication series

NameProceedings of SSST 2014 - 8th Workshop on Syntax, Semantics and Structure in Statistical Translation

Conference

Conference8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2014
Country/TerritoryQatar
CityDoha
Period10/25/14 → …

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'On the properties of neural machine translation: Encoder–decoder approaches'. Together they form a unique fingerprint.

Cite this