Show simple item record

dc.contributor.authorCOHN, TREVORen_US
dc.contributor.authorBlunsom, Philen_US
dc.date.accessioned2014-05-22T10:19:10Z
dc.date.available2014-05-22T10:19:10Z
dc.date.issued2005en_US
dc.date.submitted2005-05-23en_US
dc.identifier.citationCohn, T., & Blunsom, P. (2005). Semantic role labelling with tree conditional random fields. In, Proceedings, CoNLL-2005: Ninth Conference on Computational Natural Language, Ann Arbor, Michigan.en_US
dc.identifier.urihttp://hdl.handle.net/11343/33833
dc.description.abstractIn this paper we apply conditional random fields (CRFs) to the semantic role labelling task. We define a random field over the structure of each sentence's syntactic parse tree. For each node of the tree, the model must predict a semantic role label, which is interpreted as the labelling for the corresponding syntactic constituent. We show how modelling the task as a tree labelling problem allows for the use of efficient CRF inference algorithms, while also increasing generalisation performance when compared to the equivalent maximum entropy classifier. We have participated in the CoNLL-2005 shared task closed challenge with full syntactic information.en_US
dc.formatapplication/pdfen_US
dc.languageengen_US
dc.titleSemantic role labelling with tree conditional random fieldsen_US
dc.typeConference Paperen_US
melbourne.peerreviewPeer Revieweden_US
melbourne.affiliation.departmentEngineering: Department of Computer Science and Software Engineeringen_US
melbourne.publication.statusInpressen_US
melbourne.source.titleProceedings, CoNLL-2005: Ninth Conference on Computational Natural Languageen_US
melbourne.source.locationconferenceAnn Arbor, Michiganen_US
dc.description.sourcedateJune, 2005en_US
melbourne.elementsidNA
melbourne.contributor.authorCohn, Trevor
melbourne.contributor.authorBLUNSOM, PHILIP CHARLES
melbourne.accessrightsOpen Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record