Show simple item record

dc.contributor.authorTuç, Salih
dc.contributor.authorCan, Burcu
dc.date.accessioned2020-12-17T10:40:43Z
dc.date.available2020-12-17T10:40:43Z
dc.date.issued2021-03-31
dc.identifier.citationTuc, S. and Can, B. (in press) Self attended stack pointer networks for learning long term dependencies, ICON 2020: 17th International Conference on Natural Language Processing, 18th-21st December, 2020. Online.en
dc.identifier.urihttp://hdl.handle.net/2436/623834
dc.descriptionThis is an accepted manuscript of an article published by ACL in the proceedings of the 17th International Conference on Natural Language Processing (in press). The accepted version of the publication may differ from the final published version.en
dc.description.abstractWe propose a novel deep neural architecture for dependency parsing, which is built upon a Transformer Encoder (Vaswani et al., 2017) and a Stack Pointer Network (Ma et al., 2018). We first encode each sentence using a Transformer Network and then the dependency graph is generated by a Stack Pointer Network by selecting the head of each word in the sentence through a head selection process. We evaluate our model on Turkish and English treebanks. The results show that our transformer-based model learns long term dependencies efficiently compared to sequential models such as recurrent neural networks. Our self attended stack pointer network improves UAS score around 6% upon the LSTM based stack pointer (Ma et al., 2018) for Turkish sentences with a length of more than 20 words.en
dc.formatapplication/pdfen
dc.language.isoenen
dc.publisherAssociation for Computational Linguisticsen
dc.relation.urlhttp://www.iitp.ac.in/~ai-nlp-ml/icon2020/proceedings.htmlen
dc.subjectdependency parsingen
dc.subjectdeep learningen
dc.subjectsyntaxen
dc.titleSelf attended stack pointer networks for learning long term dependenciesen
dc.typeConference contributionen
dc.date.updated2020-12-15T19:27:18Z
dc.conference.nameICON 2020: 17th International Conference on Natural Language Processing
dc.conference.locationVirtual
pubs.finish-date2020-12-21
pubs.start-date2020-12-18
dc.date.accepted2020-12-01
rioxxterms.funderUniversity of Wolverhamptonen
rioxxterms.identifier.projectUOW17122020BCen
rioxxterms.versionAMen
rioxxterms.licenseref.urihttps://creativecommons.org/licenses/by/4.0/en
rioxxterms.licenseref.startdate2021-12-31en
refterms.dateFCD2020-12-17T10:35:49Z
refterms.versionFCDAM


Files in this item

Thumbnail
Name:
Tuc_Can_Self_appointed_stack_p ...
Embargo:
2021-12-31
Size:
615.9Kb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by/4.0/