Document-level Neural MT: A Systematic Comparison

António V. Lopes, M. Amin Farajian, Rachel Bawden, Michael Zhang, André F. T. Martins

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

Abstract

In this paper we provide a systematic comparison of existing and new document-level neural machine translation solutions. As part of this comparison, we introduce and evaluate a document-level variant of the recently proposed Star Transformer architecture. In addition to using the traditional metric BLEU, we report the accuracy of the models in handling anaphoric pronoun translation as well as coherence and cohesion using contrastive test sets. Finally, we report the results of human evaluation in terms of Multidimensional Quality Metrics (MQM) and analyse the correlation of the results obtained by the automatic metrics with human judgments.
Original languageEnglish
Title of host publicationProceedings of the 22nd Annual Conference of the European Association for Machine Translation
Place of PublicationLisboa, Portugal
PublisherEuropean Association for Machine Translation
Pages225–234
Number of pages10
ISBN (Electronic)978-989-33-0589-8
Publication statusPublished - 6 May 2020
Event22nd Annual Conference of the European Association for Machine Translation - Online Conference in place of Instituto Superior Técnico, Lisbon, Portugal
Duration: 3 Nov 20205 Nov 2020
https://eamt2020.inesc-id.pt/

Conference

Conference22nd Annual Conference of the European Association for Machine Translation
Abbreviated titleEAMT 2020
Period3/11/205/11/20
Internet address

Keywords

  • Machine translation
  • Document-level machine translation
  • Neural machine translation
  • Context
  • Evaluation
  • anaphora
  • lexical choice

Fingerprint Dive into the research topics of 'Document-level Neural MT: A Systematic Comparison'. Together they form a unique fingerprint.

Cite this