Loading...
Findings of the WMT 2018 shared task on quality estimation
Specia, Lucia Blain, Frederic Logacheva, Varvara Astudillo, Ramón Martins, André
Specia, Lucia
Blain, Frederic
Logacheva, Varvara
Astudillo, Ramón
Martins, André
Editors
Other contributors
Affiliation
Epub Date
Issue Date
2018-11
Submitted date
Subjects
Alternative
Abstract
We report the results of the WMT18 shared task on Quality Estimation, i.e. the task of predicting the quality of the output of machine translation systems at various granularity levels: word, phrase, sentence and document. This year we include four language pairs, three text domains, and translations produced by both statistical and neural machine translation systems. Participating teams from ten institutions submitted a variety of systems to different task variants and language pairs.
Citation
Specia, L., Blain, F., Logacheva, V., Astudillo, R. et al. (2018) Findings of the WMT 2018 shared task on quality estimation. In Proceedings of the Third Conference on Machine Translation, Shared Task Papers, Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel et al. (Eds.), Belgium, Brussels: Association for Computational Linguistics, pp. 689-709.
Journal
Research Unit
PubMed ID
PubMed Central ID
Embedded videos
Additional Links
Type
Conference contribution
Language
en
Description
© 2018 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/W18-6451
Series/Report no.
ISSN
EISSN
ISBN
9781948087810
ISMN
Gov't Doc #
Sponsors
The data and annotations collected for Tasks 1, 2 and 3 was supported by the EC H2020 QT21 project (grant agreement no. 645452). The shared task organisation was also supported by the QT21 project, national funds through Fundacao para a Ciencia e Tecnologia (FCT), with references UID/CEC/50021/2013 and UID/EEA/50008/2013, and by the European Research Council (ERC StG DeepSPIN 758969). We would also like to thank Julie Beliao and the Unbabel Quality Team for coordinating the annotation of the dataset used in Task 4.