Show simple item record

dc.contributor.authorSu, Y
dc.contributor.authorCai, D
dc.contributor.authorZhou, Q
dc.contributor.authorLin, Z
dc.contributor.authorBaker, S
dc.contributor.authorCao, Y
dc.contributor.authorShi, S
dc.contributor.authorCollier, N
dc.contributor.authorWang, Y
dc.date.accessioned2022-05-27T23:30:35Z
dc.date.available2022-05-27T23:30:35Z
dc.date.issued2021
dc.identifier.isbn9781954085527
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/337573
dc.description.abstractWe study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical curriculum learning framework that trains the matching model in an “easy-to-difficult” scheme. Our learning framework consists of two complementary curricula: (1) corpus-level curriculum (CC); and (2) instance-level curriculum (IC). In CC, the model gradually increases its ability in finding the matching clues between the dialogue context and a response candidate. As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate. Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.
dc.publisherAssociation for Computational Linguistics
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleDialogue response selection with hierarchical curriculum learning
dc.typeConference Object
dc.publisher.departmentDepartment of Theoretical & Applied Linguistics
dc.publisher.departmentFaculty of Modern And Medieval Languages And Linguistics
dc.date.updated2022-05-27T06:34:45Z
prism.endingPage1751
prism.publicationDate2021
prism.publicationNameACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
prism.startingPage1740
dc.identifier.doi10.17863/CAM.84982
dcterms.dateAccepted2021-05-05
rioxxterms.versionofrecord10.18653/v1/2021.acl-long.137
rioxxterms.versionVoR
dc.contributor.orcidSu, Yixuan [0000-0002-1472-7791]
dc.contributor.orcidCollier, Nigel [0000-0002-7230-4164]
pubs.conference-nameProceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
pubs.conference-start-date2021-08
cam.orpheus.success2022-06-22
cam.orpheus.counter3
cam.depositDate2022-05-27
pubs.conference-finish-date2021-08
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Attribution 4.0 International
Except where otherwise noted, this item's licence is described as Attribution 4.0 International