Investigating alignment interpretability for low-resource NMT

Boito, M.Z., Villavicencio, A. orcid.org/0000-0002-3731-9168 and Besacier, L. (2021) Investigating alignment interpretability for low-resource NMT. Machine Translation, 34. pp. 305-323. ISSN 0922-6567

Abstract

Metadata

Item Type: Article
Authors/Creators:
Copyright, Publisher and Additional Information:

© The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature 2021. This is an author-produced version of a paper subsequently published in Machine Translation. Uploaded in accordance with the publisher's self-archiving policy.

Keywords: low-resource languages; attention mechanism; sequence-to-sequence models; unsupervised word segmentation; computational language documentation; neural machine translation
Dates:
  • Published: 6 February 2021
  • Published (online): 6 February 2021
  • Accepted: 11 December 2020
Institution: The University of Sheffield
Academic Units: The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield)
Funding Information:
Funder
Grant number
Engineering and Physical Science Research Council
EP/T02450X/1
Depositing User: Symplectic Sheffield
Date Deposited: 19 Oct 2020 10:29
Last Modified: 06 Feb 2022 01:38
Status: Published
Publisher: Springer
Refereed: Yes
Identification Number: 10.1007/s10590-020-09254-w
Open Archives Initiative ID (OAI ID):

Export

Statistics