Show simple item record

Files in this item

Thumbnail
Name:
Nederhof_2021_Calculating_the_optimal_step_EACL_2273_CCBY.pdf
Size:
354.5Kb
Format:
PDF
View/Open

Calculating the optimal step of arc-eager parsing for non-projective trees

Item metadata

dc.contributor.authorNederhof, Mark Jan
dc.date.accessioned2021-04-22T10:30:07Z
dc.date.available2021-04-22T10:30:07Z
dc.date.issued2021-04-19
dc.identifier272452458
dc.identifier794119bc-d383-40c6-8171-8a4b5fab3ac0
dc.identifier85107290251
dc.identifier000863557002029
dc.identifier.citationNederhof , M J 2021 , Calculating the optimal step of arc-eager parsing for non-projective trees . in Proceedings of the 16th Conference of the European Chapter of the Association of Computational Linguistics (EACL 2021) . Association for Computational Linguistics , pp. 2273–2283 , 16th Conference of the European Chapter of the ACL , Kyiv , Ukraine , 19/04/21 . < https://www.aclweb.org/anthology/2021.eacl-main.193 >en
dc.identifier.citationconferenceen
dc.identifier.isbn9781954085022
dc.identifier.otherORCID: /0000-0002-1845-6829/work/92774989
dc.identifier.urihttps://hdl.handle.net/10023/23073
dc.description.abstractIt is shown that the optimal next step of an arc-eager parser relative to a non-projective dependency structure can be calculated in cubic time, solving an open problem in parsing theory. Applications are in training of parsers by means of a 'dynamic oracle'.
dc.format.extent363063
dc.language.isoeng
dc.publisherAssociation for Computational Linguistics
dc.relation.ispartofProceedings of the 16th Conference of the European Chapter of the Association of Computational Linguistics (EACL 2021)en
dc.subjectP Language and Literatureen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectNSen
dc.subjectNISen
dc.subject.lccPen
dc.subject.lccQA75en
dc.titleCalculating the optimal step of arc-eager parsing for non-projective treesen
dc.typeConference itemen
dc.contributor.institutionUniversity of St Andrews. School of Computer Scienceen
dc.identifier.urlhttps://www.aclweb.org/anthology/2021.eacl-main.193en


This item appears in the following Collection(s)

Show simple item record

Items in the St Andrews Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.