A Neural Local Coherence Model

<p dir="ltr">We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the powe...

Full description

Saved in:
Bibliographic Details
Main Author: Dat Tien Nguyen (19720057) (author)
Other Authors: Shafiq Joty (4576078) (author)
Published: 2017
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513557082669056
author Dat Tien Nguyen (19720057)
author2 Shafiq Joty (4576078)
author2_role author
author_facet Dat Tien Nguyen (19720057)
Shafiq Joty (4576078)
author_role author
dc.creator.none.fl_str_mv Dat Tien Nguyen (19720057)
Shafiq Joty (4576078)
dc.date.none.fl_str_mv 2017-01-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.18653/v1/p17-1121
dc.relation.none.fl_str_mv https://figshare.com/articles/conference_contribution/A_Neural_Local_Coherence_Model/27082693
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
Local Coherence Model
Convolutional Neural Network (CNN)
Entity Grid Representation
Entity-Specific Features
Distributed Representation
Pairwise Ranking Method
End-to-End Training
dc.title.none.fl_str_mv A Neural Local Coherence Model
dc.type.none.fl_str_mv Text
Conference contribution
info:eu-repo/semantics/publishedVersion
text
conference object
description <p dir="ltr">We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See conference contribution on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p17-1121" target="_blank">https://dx.doi.org/10.18653/v1/p17-1121</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017</p>
eu_rights_str_mv openAccess
id Manara2_560c53ac99accc431e2237656c53bacc
identifier_str_mv 10.18653/v1/p17-1121
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27082693
publishDate 2017
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Neural Local Coherence ModelDat Tien Nguyen (19720057)Shafiq Joty (4576078)Information and computing sciencesArtificial intelligenceMachine learningLanguage, communication and cultureLinguisticsLocal Coherence ModelConvolutional Neural Network (CNN)Entity Grid RepresentationEntity-Specific FeaturesDistributed RepresentationPairwise Ranking MethodEnd-to-End Training<p dir="ltr">We propose a local coherence model based on a convolutional neural network that operates over the entity grid representation of a text. The model captures long range entity transitions along with entity-specific features without loosing generalization, thanks to the power of distributed representation. We present a pairwise ranking method to train the model in an end-to-end fashion on a task and learn task-specific high level features. Our evaluation on three different coherence assessment tasks demonstrates that our model achieves state of the art results outperforming existing models by a good margin.</p><h2>Other Information</h2><p dir="ltr">Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See conference contribution on publisher's website: <a href="https://dx.doi.org/10.18653/v1/p17-1121" target="_blank">https://dx.doi.org/10.18653/v1/p17-1121</a></p><p dir="ltr">Conference information: 55th Annual Meeting of the Association for Computational Linguistics (Short Papers), pages 518–523 Vancouver, Canada, July 30 - August 4, 2017</p>2017-01-01T00:00:00ZTextConference contributioninfo:eu-repo/semantics/publishedVersiontextconference object10.18653/v1/p17-1121https://figshare.com/articles/conference_contribution/A_Neural_Local_Coherence_Model/27082693CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/270826932017-01-01T00:00:00Z
spellingShingle A Neural Local Coherence Model
Dat Tien Nguyen (19720057)
Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
Local Coherence Model
Convolutional Neural Network (CNN)
Entity Grid Representation
Entity-Specific Features
Distributed Representation
Pairwise Ranking Method
End-to-End Training
status_str publishedVersion
title A Neural Local Coherence Model
title_full A Neural Local Coherence Model
title_fullStr A Neural Local Coherence Model
title_full_unstemmed A Neural Local Coherence Model
title_short A Neural Local Coherence Model
title_sort A Neural Local Coherence Model
topic Information and computing sciences
Artificial intelligence
Machine learning
Language, communication and culture
Linguistics
Local Coherence Model
Convolutional Neural Network (CNN)
Entity Grid Representation
Entity-Specific Features
Distributed Representation
Pairwise Ranking Method
End-to-End Training