Skip to main navigation Skip to search Skip to main content

Improving the transformer translation model with document-level context

  • Jiacheng Zhang
  • , Huanbo Luan
  • , Maosong Sun
  • , Fei Fei Zhai
  • , Jingfang Xu
  • , Min Zhang
  • , Yang Liu*
  • *Corresponding author for this work
  • Tsinghua University
  • Sohu, Inc.
  • Soochow University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer still remains a challenge. In this work, we extend the Transformer model with a new context encoder to represent document-level context, which is then incorporated into the original encoder and decoder. As large-scale document-level parallel corpora are usually not available, we introduce a two-step training method to take full advantage of abundant sentence-level parallel corpora and limited document-level parallel corpora. Experiments on the NIST Chinese-English datasets and the IWSLT French-English datasets show that our approach improves over Transformer significantly.

Original languageEnglish
Title of host publicationProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
EditorsEllen Riloff, David Chiang, Julia Hockenmaier, Jun'ichi Tsujii
PublisherAssociation for Computational Linguistics
Pages533-542
Number of pages10
ISBN (Electronic)9781948087841
StatePublished - 2018
Externally publishedYes
Event2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, Belgium
Duration: 31 Oct 20184 Nov 2018

Publication series

NameProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Conference

Conference2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Country/TerritoryBelgium
CityBrussels
Period31/10/184/11/18

Fingerprint

Dive into the research topics of 'Improving the transformer translation model with document-level context'. Together they form a unique fingerprint.

Cite this