Show simple item record

dc.contributor.authorRei, Marek
dc.contributor.authorSogaard, Anders
dc.contributor.authorAAAI
dc.date.accessioned2019-01-18T00:30:57Z
dc.date.available2019-01-18T00:30:57Z
dc.date.issued2019
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/288161
dc.description.abstractLearning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language composition can allow us to guide the models based on existing knowledge, regularizing them towards more robust and interpretable representations. In this paper, we investigate how objectives at different granularities can be used to learn better language representations and we propose an architecture for jointly learning to label sentences and tokens. The predictions at each level are combined together using an attention mechanism, with token-level labels also acting as explicit supervision for composing sentence-level representations. Our experiments show that by learning to perform these tasks jointly on multiple levels, the model achieves substantial improvements for both sentence classification and sequence labeling.
dc.titleJointly Learning to Label Sentences and Tokens
dc.typeConference Object
prism.endingPage6923
prism.publicationDate2019
prism.publicationNameTHIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
prism.startingPage6916
dc.identifier.doi10.17863/CAM.35477
dcterms.dateAccepted2018-10-31
rioxxterms.versionofrecord10.17863/CAM.35477
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2019
rioxxterms.typeConference Paper/Proceeding/Abstract
pubs.funder-project-idCambridge Assessment (unknown)
pubs.conference-nameAAAI 2019
cam.orpheus.successThu Nov 05 11:53:21 GMT 2020 - Embargo updated
rioxxterms.freetoread.startdate2020-12-31


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record