Skip to main navigation Skip to search Skip to main content

Semantic Structural Decomposition for Neural Machine Translation

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

10 Scopus citations

Abstract

Building on recent advances in semantic parsing and text simplification, we investigate the use of semantic splitting of the source sentence as preprocessing for machine translation. We experiment with a Transformer model and evaluate using large-scale crowd-sourcing experiments. Results show a significant increase in fluency on long sentences on an English-to-French setting with a training corpus of 5M sentence pairs, while retaining comparable adequacy.

Original languageEnglish
Title of host publicationCOLING 2020 - SEM 2020
Subtitle of host publication9th Conference on Lexical and Computational Semantics, Proceedings of the Conference
EditorsIryna Gurevych, Marianna Apidianaki, Manaal Faruqui
PublisherAssociation for Computational Linguistics (ACL)
Pages50-57
Number of pages8
ISBN (Electronic)9781952148323
StatePublished - 1 Jan 2020
Externally publishedYes
Event9th Joint Conference on Lexical and Computational Semantics, SEM 2020 - Hybrid, Barcelona, Spain
Duration: 12 Dec 202013 Dec 2020

Publication series

NameCOLING 2020 - SEM 2020: 9th Conference on Lexical and Computational Semantics, Proceedings of the Conference

Conference

Conference9th Joint Conference on Lexical and Computational Semantics, SEM 2020
Country/TerritorySpain
CityHybrid, Barcelona
Period12/12/2013/12/20

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Semantic Structural Decomposition for Neural Machine Translation'. Together they form a unique fingerprint.

Cite this