Knowledge distillation for quality estimation
dc.contributor.author | Gajbhiye, Amit | |
dc.contributor.author | Fomicheva, Marina | |
dc.contributor.author | Alva-Manchego, Fernando | |
dc.contributor.author | Blain, Frederic | |
dc.contributor.author | Obamuyide, Abiola | |
dc.contributor.author | Aletras, Nikolaos | |
dc.contributor.author | Specia, Lucia | |
dc.date.accessioned | 2021-06-08T09:45:56Z | |
dc.date.available | 2021-06-08T09:45:56Z | |
dc.date.issued | 2021-08-01 | |
dc.identifier.citation | Gajbhiye, A., Fomicheva, M., Alva-Manchego, F., Blain, F., Obamuyide, A., Aletras, N. & Specia, L. (2021) Knowledge distillation for quality estimation. In: Zong, C., Xia, F., Li, W. and Navigli, R., (eds.) Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 01-06 Aug 2021, Bangkok, Thailand (virtual conference). Association for Computational Linguistics (ACL) , pp. 5091-5099. | en |
dc.identifier.doi | 10.18653/v1/2021.findings-acl.452 | |
dc.identifier.uri | http://hdl.handle.net/2436/624102 | |
dc.description | © 2021 The Authors. Published by ACL. 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: https://aclanthology.org/2021.findings-acl.452 | en |
dc.description.abstract | Quality Estimation (QE) is the task of automatically predicting Machine Translation quality in the absence of reference translations, making it applicable in real-time settings, such as translating online social media conversations. Recent success in QE stems from the use of multilingual pre-trained representations, where very large models lead to impressive results. However, the inference time, disk and memory requirements of such models do not allow for wide usage in the real world. Models trained on distilled pre-trained representations remain prohibitively large for many usage scenarios. We instead propose to directly transfer knowledge from a strong QE teacher model to a much smaller model with a different, shallower architecture. We show that this approach, in combination with data augmentation, leads to light-weight QE models that perform competitively with distilled pre-trained representations with 8x fewer parameters. | en |
dc.format | application/pdf | en |
dc.language.iso | en | en |
dc.publisher | Association for Computational Linguistics | en |
dc.relation.url | https://2021.aclweb.org/ | en |
dc.subject | quality estimation | en |
dc.subject | machine translation | en |
dc.subject | knowledge distillation | en |
dc.title | Knowledge distillation for quality estimation | en |
dc.type | Conference contribution | en |
dc.date.updated | 2021-06-07T13:44:55Z | |
dc.conference.name | 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) | |
pubs.finish-date | 2021-08-04 | |
pubs.start-date | 2021-08-02 | |
dc.date.accepted | 2021-05-06 | |
rioxxterms.funder | University of Wolverhampton | en |
rioxxterms.identifier.project | UOW08062021FB | en |
rioxxterms.version | VoR | en |
rioxxterms.licenseref.uri | https://creativecommons.org/licenses/by/4.0/ | en |
rioxxterms.licenseref.startdate | 2021-08-01 | en |
dc.source.beginpage | 5091 | |
dc.source.endpage | 5099 | |
refterms.dateFCD | 2021-06-08T09:43:44Z | |
refterms.versionFCD | VoR | |
refterms.dateFOA | 2021-08-01T00:00:00Z |