Coherence modeling of asynchronous conversations

A neural entity grid approach

Tasnim Mohiuddin, Shafiq Rayhan Joty, Dat Tien Nguyen

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

2 Citations (Scopus)

Abstract

We propose a novel coherence model for written asynchronous conversations (e.g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks. We conduct our research in two steps. First, we propose improvements to the recently proposed neural entity grid model by lexicalizing its entity transitions. Then, we extend the model to asynchronous conversations by incorporating the underlying conversational structure in the entity grid representation and feature computation. Our model achieves state of the art results on standard coherence assessment tasks in monologue and conversations outperforming existing models. We also demonstrate its effectiveness in reconstructing thread structures.

Original languageEnglish
Title of host publicationACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
PublisherAssociation for Computational Linguistics (ACL)
Pages558-568
Number of pages11
ISBN (Electronic)9781948087322
Publication statusPublished - 1 Jan 2018
Event56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia
Duration: 15 Jul 201820 Jul 2018

Publication series

NameACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume1

Conference

Conference56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
CountryAustralia
CityMelbourne
Period15/7/1820/7/18

Fingerprint

Electronic mail

ASJC Scopus subject areas

  • Software
  • Computational Theory and Mathematics

Cite this

Mohiuddin, T., Rayhan Joty, S., & Nguyen, D. T. (2018). Coherence modeling of asynchronous conversations: A neural entity grid approach. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 558-568). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1). Association for Computational Linguistics (ACL).

Coherence modeling of asynchronous conversations : A neural entity grid approach. / Mohiuddin, Tasnim; Rayhan Joty, Shafiq; Nguyen, Dat Tien.

ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. p. 558-568 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1).

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

Mohiuddin, T, Rayhan Joty, S & Nguyen, DT 2018, Coherence modeling of asynchronous conversations: A neural entity grid approach. in ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 1, Association for Computational Linguistics (ACL), pp. 558-568, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 15/7/18.
Mohiuddin T, Rayhan Joty S, Nguyen DT. Coherence modeling of asynchronous conversations: A neural entity grid approach. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL). 2018. p. 558-568. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).
Mohiuddin, Tasnim ; Rayhan Joty, Shafiq ; Nguyen, Dat Tien. / Coherence modeling of asynchronous conversations : A neural entity grid approach. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. pp. 558-568 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).
@inproceedings{d8d21061f17e4b2b82307f994978c21e,
title = "Coherence modeling of asynchronous conversations: A neural entity grid approach",
abstract = "We propose a novel coherence model for written asynchronous conversations (e.g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks. We conduct our research in two steps. First, we propose improvements to the recently proposed neural entity grid model by lexicalizing its entity transitions. Then, we extend the model to asynchronous conversations by incorporating the underlying conversational structure in the entity grid representation and feature computation. Our model achieves state of the art results on standard coherence assessment tasks in monologue and conversations outperforming existing models. We also demonstrate its effectiveness in reconstructing thread structures.",
author = "Tasnim Mohiuddin and {Rayhan Joty}, Shafiq and Nguyen, {Dat Tien}",
year = "2018",
month = "1",
day = "1",
language = "English",
series = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",
publisher = "Association for Computational Linguistics (ACL)",
pages = "558--568",
booktitle = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

}

TY - GEN

T1 - Coherence modeling of asynchronous conversations

T2 - A neural entity grid approach

AU - Mohiuddin, Tasnim

AU - Rayhan Joty, Shafiq

AU - Nguyen, Dat Tien

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We propose a novel coherence model for written asynchronous conversations (e.g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks. We conduct our research in two steps. First, we propose improvements to the recently proposed neural entity grid model by lexicalizing its entity transitions. Then, we extend the model to asynchronous conversations by incorporating the underlying conversational structure in the entity grid representation and feature computation. Our model achieves state of the art results on standard coherence assessment tasks in monologue and conversations outperforming existing models. We also demonstrate its effectiveness in reconstructing thread structures.

AB - We propose a novel coherence model for written asynchronous conversations (e.g., forums, emails), and show its applications in coherence assessment and thread reconstruction tasks. We conduct our research in two steps. First, we propose improvements to the recently proposed neural entity grid model by lexicalizing its entity transitions. Then, we extend the model to asynchronous conversations by incorporating the underlying conversational structure in the entity grid representation and feature computation. Our model achieves state of the art results on standard coherence assessment tasks in monologue and conversations outperforming existing models. We also demonstrate its effectiveness in reconstructing thread structures.

UR - http://www.scopus.com/inward/record.url?scp=85059266266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059266266&partnerID=8YFLogxK

M3 - Conference contribution

T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 558

EP - 568

BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

PB - Association for Computational Linguistics (ACL)

ER -