Show simple item record

dc.contributor.authorSu, Yixuan
dc.contributor.authorMeng, Z
dc.contributor.authorBaker, S
dc.contributor.authorCollier, Nigel
dc.date.accessioned2022-05-27T23:30:38Z
dc.date.available2022-05-27T23:30:38Z
dc.date.issued2021-01-01
dc.identifier.isbn9781955917100
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/337574
dc.description.abstractNeural table-to-text generation models have achieved remarkable progress on an array of tasks. However, due to the data-hungry nature of neural models, their performances strongly rely on large-scale training examples, limiting their applicability in real-world applications. To address this, we propose a new framework: Prototype-to-Generate (P2G), for table-to-text generation under the few-shot scenario. The proposed framework utilizes the retrieved prototypes, which are jointly selected by an IR system and a novel prototype selector to help the model bridging the structural gap between tables and texts. Experimental results on three benchmark datasets with three state-of-the-art models demonstrate that the proposed framework significantly improves the model performance across various evaluation metrics.
dc.rightsAttribution 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.titleFew-Shot Table-to-Text Generation with Prototype Memory
dc.typeConference Object
dc.publisher.departmentDepartment of Theoretical & Applied Linguistics
dc.publisher.departmentFaculty of Modern And Medieval Languages And Linguistics
dc.date.updated2022-05-27T06:36:32Z
prism.endingPage917
prism.publicationDate2021
prism.publicationNameFindings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
prism.startingPage910
dc.identifier.doi10.17863/CAM.84983
rioxxterms.versionofrecord10.17863/CAM.84983
rioxxterms.versionVoR
dc.contributor.orcidSu, Yixuan [0000-0002-1472-7791]
dc.contributor.orcidCollier, Nigel [0000-0002-7230-4164]
cam.orpheus.counter9*
cam.depositDate2022-05-27
pubs.licence-identifierapollo-deposit-licence-2-1
pubs.licence-display-nameApollo Repository Deposit Licence Agreement
rioxxterms.freetoread.startdate2100-01-01


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