Show simple item record

dc.contributor.authorZhang, Yuan
dc.contributor.authorBarzilay, Regina
dc.contributor.authorJaakkola, Tommi
dc.date.accessioned2021-10-27T20:10:34Z
dc.date.available2021-10-27T20:10:34Z
dc.date.issued2017
dc.identifier.urihttps://hdl.handle.net/1721.1/135065
dc.description.abstract<jats:p> We introduce a neural method for transfer learning between two (source and target) classification tasks or aspects over the same domain. Rather than training on target labels, we use a few keywords pertaining to source and target aspects indicating sentence relevance instead of document class labels. Documents are encoded by learning to embed and softly select relevant sentences in an aspect-dependent manner. A shared classifier is trained on the source encoded documents and labels, and applied to target encoded documents. We ensure transfer through aspect-adversarial training so that encoded documents are, as sets, aspect-invariant. Experimental results demonstrate that our approach outperforms different baselines and model variants on two datasets, yielding an improvement of 27% on a pathology dataset and 5% on a review dataset. </jats:p>
dc.language.isoen
dc.publisherMIT Press - Journals
dc.relation.isversionof10.1162/TACL_A_00077
dc.rightsCreative Commons Attribution 4.0 International license
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.sourceMIT Press
dc.titleAspect-augmented Adversarial Networks for Domain Adaptation
dc.typeArticle
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
dc.relation.journalTransactions of the Association for Computational Linguistics
dc.eprint.versionFinal published version
dc.type.urihttp://purl.org/eprint/type/ConferencePaper
eprint.statushttp://purl.org/eprint/status/NonPeerReviewed
dc.date.updated2019-05-07T15:38:17Z
dspace.orderedauthorsZhang, Y; Barzilay, R; Jaakkola, T
dspace.date.submission2019-05-07T15:38:19Z
mit.journal.volume5
mit.metadata.statusAuthority Work and Publication Information Needed


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record