Show simple item record

Files in this item

Thumbnail
Name:
Nederhof_2019_Calculating_optimal_TACL_283_CC.pdf
Size:
826.1Kb
Format:
PDF
View/Open

Calculating the optimal step in shift-reduce dependency parsing : from cubic to linear time

Item metadata

dc.contributor.authorNederhof, Mark Jan
dc.date.accessioned2019-06-04T10:30:03Z
dc.date.available2019-06-04T10:30:03Z
dc.date.issued2019-05-31
dc.identifier259065142
dc.identifier309939cb-5253-4ef3-91c8-bda773cea8f2
dc.identifier85107273555
dc.identifier.citationNederhof , M J 2019 , ' Calculating the optimal step in shift-reduce dependency parsing : from cubic to linear time ' , Transactions of the Association for Computational Linguistics , vol. 7 , pp. 283-296 . https://doi.org/10.1162/tacl_a_00268en
dc.identifier.issn2307-387X
dc.identifier.otherORCID: /0000-0002-1845-6829/work/58531291
dc.identifier.urihttps://hdl.handle.net/10023/17811
dc.description.abstractWe present a new cubic-time algorithm to calculate the optimal next step in shift-reduce dependency parsing, relative to ground truth, commonly referred to as dynamic oracle. Unlike existing algorithms, it is applicable if the training corpus contains non-projective structures. We then show that for a projective training corpus, the time complexity can be improved from cubic to linear.
dc.format.extent14
dc.format.extent846011
dc.language.isoeng
dc.relation.ispartofTransactions of the Association for Computational Linguisticsen
dc.subjectFormal language theoryen
dc.subjectAutomata theoryen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectComputational Theory and Mathematicsen
dc.subjectT-NDASen
dc.subjectBDCen
dc.subjectR2Cen
dc.subject~DC~en
dc.subject.lccQA75en
dc.titleCalculating the optimal step in shift-reduce dependency parsing : from cubic to linear timeen
dc.typeJournal articleen
dc.contributor.institutionUniversity of St Andrews. School of Computer Scienceen
dc.identifier.doi10.1162/tacl_a_00268
dc.description.statusPeer revieweden


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.