Skip to main content
DORAS
DCU Online Research Access Service
Login (DCU Staff Only)
Investigating 'Aspect' in NMT and SMT: translating the English simple past and present perfect

Vanmassenhove, Eva ORCID: 0000-0003-1162-820X, Du, Jinhua ORCID: 0000-0002-3267-4881 and Way, Andy ORCID: 0000-0001-5736-5930 (2017) Investigating 'Aspect' in NMT and SMT: translating the English simple past and present perfect. Computational Linguistics in the Netherlands Journal (CLIN), 7 . pp. 109-128. ISSN 2211-4009

Full text available as:

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
353kB

Abstract

One of the important differences between English and French grammar is related to how their verbal systems handle aspectual information. While the English simple past tense is aspectually neutral, the French and Spanish past tenses are linked with a particular imperfective/perfective aspect. This study examines what Statistical Machine Translation (SMT) and Neural Machine Translation (NMT) learn about 'aspect'and how this is reflected in the translations they produce. We use their main knowledge sources, phrase-tables (SMT) and encoding vectors (NMT), to examine what kind of aspectual information they encode. Furthermore, we examine whether this encoded 'knowledge'is actually transferred during decoding and thus reflected in the actual translations. Our study is based on the translations of the English simple past and present perfect tenses into French and Spanish …

Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:Natural Language Processing Linguistics
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Research Initiatives and Centres > ADAPT
Publisher:CLIN
Official URL:https://clinjournal.org/clinj/article/view/73
Copyright Information:© 2017 CLIN
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland (SFI) Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund.
ID Code:24606
Deposited On:06 Jul 2020 12:06 by Vidatum Academic . Last Modified 18 Nov 2020 12:55

Downloads

Downloads per month over past year

Archive Staff Only: edit this record

Altmetric
- Altmetric
+ Altmetric
  • Student Email
  • Staff Email
  • Student Apps
  • Staff Apps
  • Loop
  • Disclaimer
  • Privacy
  • Contact Us