Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations

Bushra Algotiml; AbdelRahim A. Elmadany; Walid Magdy

doi:10.18653/v1/W19-4620

Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations

Bushra Algotiml, AbdelRahim A. Elmadany, Walid Magdy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Speech acts are the actions that a speaker intends when performing an utterance within conversations. In this paper, we proposed speech act classification for asynchronous conversations on Twitter using multiple machine learning methods including SVM and deep neural networks. We applied the proposed methods on the ArSAS tweets dataset. The obtained results show that superiority of deep learning methods compared to SVMs, where Bi-LSTM managed to achieve an accuracy of 87.5% and a macro-averaged F1 score 61.5%. We believe that our results are the first to be reported on the task of speech-act recognition for asynchronous conversations on Arabic Twitter.

Original language	English
Title of host publication	Proceedings of the Fourth Arabic Natural Language Processing Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	183-191
Number of pages	9
ISBN (Electronic)	978-1-950737-32-1
DOIs	https://doi.org/10.18653/v1/W19-4620
Publication status	Published - 2 Aug 2019
Event	The Fourth Arabic Natural Language Processing Workshop - Florence, Italy Duration: 1 Aug 2019 → 2 Aug 2019 Conference number: 4 http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=83625&copyownerid=320

Workshop

Workshop	The Fourth Arabic Natural Language Processing Workshop
Abbreviated title	WANLP 2019
Country/Territory	Italy
City	Florence
Period	1/08/19 → 2/08/19
Internet address	http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=83625&copyownerid=320

Access to Document

10.18653/v1/W19-4620Licence: Creative Commons: Attribution (CC-BY)

Arabic Tweet-Act_MAGDY_DoA240519_AFVAccepted author manuscript, 127 KB
Arabic Tweet-Act_ALGOTIML_DOA25102019_VOR_CC-BYFinal published version, 198 KBLicence: Creative Commons: Attribution (CC-BY)

https://www.aclweb.org/anthology/W19-4620Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{43b2bffe97354cc8824f2e9d3dce6945,

title = "Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations",

abstract = "Speech acts are the actions that a speaker intends when performing an utterance within conversations. In this paper, we proposed speech act classification for asynchronous conversations on Twitter using multiple machine learning methods including SVM and deep neural networks. We applied the proposed methods on the ArSAS tweets dataset. The obtained results show that superiority of deep learning methods compared to SVMs, where Bi-LSTM managed to achieve an accuracy of 87.5% and a macro-averaged F1 score 61.5%. We believe that our results are the first to be reported on the task of speech-act recognition for asynchronous conversations on Arabic Twitter.",

author = "Bushra Algotiml and Elmadany, {AbdelRahim A.} and Walid Magdy",

year = "2019",

month = aug,

day = "2",

doi = "10.18653/v1/W19-4620",

language = "English",

pages = "183--191",

booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",

publisher = "Association for Computational Linguistics (ACL)",

note = "The Fourth Arabic Natural Language Processing Workshop, WANLP 2019 ; Conference date: 01-08-2019 Through 02-08-2019",

url = "http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=83625&copyownerid=320",

}

Algotiml, B, Elmadany, AA & Magdy, W 2019, Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations. in Proceedings of the Fourth Arabic Natural Language Processing Workshop. Association for Computational Linguistics (ACL), pp. 183-191, The Fourth Arabic Natural Language Processing Workshop, Florence, Italy, 1/08/19. https://doi.org/10.18653/v1/W19-4620

TY - GEN

T1 - Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations

AU - Algotiml, Bushra

AU - Elmadany, AbdelRahim A.

AU - Magdy, Walid

N1 - Conference code: 4

PY - 2019/8/2

Y1 - 2019/8/2

N2 - Speech acts are the actions that a speaker intends when performing an utterance within conversations. In this paper, we proposed speech act classification for asynchronous conversations on Twitter using multiple machine learning methods including SVM and deep neural networks. We applied the proposed methods on the ArSAS tweets dataset. The obtained results show that superiority of deep learning methods compared to SVMs, where Bi-LSTM managed to achieve an accuracy of 87.5% and a macro-averaged F1 score 61.5%. We believe that our results are the first to be reported on the task of speech-act recognition for asynchronous conversations on Arabic Twitter.

AB - Speech acts are the actions that a speaker intends when performing an utterance within conversations. In this paper, we proposed speech act classification for asynchronous conversations on Twitter using multiple machine learning methods including SVM and deep neural networks. We applied the proposed methods on the ArSAS tweets dataset. The obtained results show that superiority of deep learning methods compared to SVMs, where Bi-LSTM managed to achieve an accuracy of 87.5% and a macro-averaged F1 score 61.5%. We believe that our results are the first to be reported on the task of speech-act recognition for asynchronous conversations on Arabic Twitter.

U2 - 10.18653/v1/W19-4620

DO - 10.18653/v1/W19-4620

M3 - Conference contribution

SP - 183

EP - 191

BT - Proceedings of the Fourth Arabic Natural Language Processing Workshop

PB - Association for Computational Linguistics (ACL)

T2 - The Fourth Arabic Natural Language Processing Workshop

Y2 - 1 August 2019 through 2 August 2019

ER -

Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this