Loading...
Multimodal quality estimation for machine translation
Okabe, Shu Blain, Frédéric Specia, Lucia
Okabe, Shu
Blain, Frédéric
Specia, Lucia
Authors
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2020-07
Submitted date
Subjects
Alternative
Abstract
We propose approaches to Quality Estimation (QE) for Machine Translation that explore both text and visual modalities for Multimodal QE. We compare various multimodality integration and fusion strategies. For both sentence-level and document-level predictions, we show that state-of-the-art neural and feature-based QE frameworks obtain better results when using the additional modality.
Citation
Okabe, S., Blain, F. and Specia, L. (2020) Multimodal quality estimation for machine translation. In, Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), Jurafsky, D., Chai, J., Schluter, N. and Tetreault, J. (eds.) Stroudsburg, PA: Association for Computational Linguistics. pp. 1233-1240
Journal
Research Unit
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Conference contribution
Language
en
Description
© 2020 The Authors. Published by Association for Computational Linguistics. This is an open access article available under a Creative Commons licence.
The published version can be accessed at the following link on the publisher’s website: http://dx.doi.org/10.18653/v1/2020.acl-main.114
Series/Report no.
ISSN
EISSN
ISBN
9781952148255
ISMN
Gov't Doc #
Sponsors
This work was supported by funding from both the Bergamot project (EU H2020 Grant No. 825303) and the MultiMT project (EU H2020 ERC Starting Grant No. 678017).