A neural local coherence model

Dat Tien Nguyen, Shafiq Rayhan Joty

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages1320-1330
Number of pages11
Volume1
ISBN (Electronic)9781945626753
DOIs
Publication statusPublished - 1 Jan 2017
Event55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada
Duration: 30 Jul 20174 Aug 2017

Other

Other55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
CountryCanada
CityVancouver
Period30/7/174/8/17

Fingerprint

neural network
ranking
coherence
Neural networks
evaluation
Entity
Evaluation
Neural Networks
Grid
Distributed Representation
Ranking
Train

ASJC Scopus subject areas

  • Language and Linguistics
  • Artificial Intelligence
  • Software
  • Linguistics and Language

Cite this

Nguyen, D. T., & Rayhan Joty, S. (2017). A neural local coherence model. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 1320-1330). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-1121

A neural local coherence model. / Nguyen, Dat Tien; Rayhan Joty, Shafiq.

ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 Association for Computational Linguistics (ACL), 2017. p. 1320-1330.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nguyen, DT & Rayhan Joty, S 2017, A neural local coherence model. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). vol. 1, Association for Computational Linguistics (ACL), pp. 1320-1330, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/7/17. https://doi.org/10.18653/v1/P17-1121
Nguyen DT, Rayhan Joty S. A neural local coherence model. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1. Association for Computational Linguistics (ACL). 2017. p. 1320-1330 https://doi.org/10.18653/v1/P17-1121
Nguyen, Dat Tien ; Rayhan Joty, Shafiq. / A neural local coherence model. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Vol. 1 Association for Computational Linguistics (ACL), 2017. pp. 1320-1330
@inproceedings{1ca549c68eb14692aa1ecb76c49374a6,
title = "A neural local coherence model",
abstract = "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.",
author = "Nguyen, {Dat Tien} and {Rayhan Joty}, Shafiq",
year = "2017",
month = "1",
day = "1",
doi = "10.18653/v1/P17-1121",
language = "English",
volume = "1",
pages = "1320--1330",
booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - A neural local coherence model

AU - Nguyen, Dat Tien

AU - Rayhan Joty, Shafiq

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85040929168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040929168&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-1121

DO - 10.18653/v1/P17-1121

M3 - Conference contribution

VL - 1

SP - 1320

EP - 1330

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

PB - Association for Computational Linguistics (ACL)

ER -