DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain

Damith Premasiri; Tharindu Ranasinghe; Wajdi Zaghouani; Ruslan Mitkov

DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain

Damith Premasiri, Tharindu Ranasinghe, Wajdi Zaghouani, Ruslan Mitkov

HBKU College of Humanities and Social Science

University of Wolverhampton

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

9 Citations (Scopus)

Abstract

The task of machine reading comprehension (MRC) is a useful benchmark to evaluate the natural language understanding of machines. It has gained popularity in the natural language processing (NLP) field mainly due to the large number of datasets released for many languages. However, the research in MRC has been understudied in several domains, including religious texts. The goal of the Qur’an QA 2022 shared task is to fill this gap by producing state-of-the-art question answering and reading comprehension research on Qur’an. This paper describes the DTW entry to the Quran QA 2022 shared task. Our methodology uses transfer learning to take advantage of available Arabic MRC data. We further improve the results using various ensemble learning strategies. Our approach provided a partial Reciprocal Rank (pRR) score of 0.49 on the test set, proving its strong performance on the task.

Original language	English
Title of host publication	5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022
Editors	Hend Al-Khalifa, Tamer Elsayed, Hamdy Mubarak, Abdulmohsen Al-Thubaity, Walid Magdy, Kareem Darwish
Publisher	European Language Resources Association (ELRA)
Pages	88-95
Number of pages	8
ISBN (Electronic)	9791095546757
Publication status	Published - 2022
Event	5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Marseille, France Duration: 20 Jun 2022 → 25 Jun 2022

Publication series

Name	5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022

Conference

Conference	5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022
Country/Territory	France
City	Marseille
Period	20/06/22 → 25/06/22

Keywords

Ensemble Learning
Machine Reading Comprehension
Qur’an
Transfer Learning
Transformers

Cite this

Premasiri, D., Ranasinghe, T., Zaghouani, W., & Mitkov, R. (2022). DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain. In H. Al-Khalifa, T. Elsayed, H. Mubarak, A. Al-Thubaity, W. Magdy, & K. Darwish (Eds.), 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022 (pp. 88-95). (5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022). European Language Resources Association (ELRA).

Premasiri, Damith ; Ranasinghe, Tharindu ; Zaghouani, Wajdi et al. / DTW at Qur’an QA 2022 : Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain. 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022. editor / Hend Al-Khalifa ; Tamer Elsayed ; Hamdy Mubarak ; Abdulmohsen Al-Thubaity ; Walid Magdy ; Kareem Darwish. European Language Resources Association (ELRA), 2022. pp. 88-95 (5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022).

@inproceedings{bfbf3a7d463a48dcbc07fb58e4a179e5,

title = "DTW at Qur{\textquoteright}an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain",

abstract = "The task of machine reading comprehension (MRC) is a useful benchmark to evaluate the natural language understanding of machines. It has gained popularity in the natural language processing (NLP) field mainly due to the large number of datasets released for many languages. However, the research in MRC has been understudied in several domains, including religious texts. The goal of the Qur{\textquoteright}an QA 2022 shared task is to fill this gap by producing state-of-the-art question answering and reading comprehension research on Qur{\textquoteright}an. This paper describes the DTW entry to the Quran QA 2022 shared task. Our methodology uses transfer learning to take advantage of available Arabic MRC data. We further improve the results using various ensemble learning strategies. Our approach provided a partial Reciprocal Rank (pRR) score of 0.49 on the test set, proving its strong performance on the task.",

keywords = "Ensemble Learning, Machine Reading Comprehension, Qur{\textquoteright}an, Transfer Learning, Transformers",

author = "Damith Premasiri and Tharindu Ranasinghe and Wajdi Zaghouani and Ruslan Mitkov",

note = "Publisher Copyright: {\textcopyright} European Language Resources Association (ELRA).; 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 ; Conference date: 20-06-2022 Through 25-06-2022",

year = "2022",

language = "English",

series = "5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022",

publisher = "European Language Resources Association (ELRA)",

pages = "88--95",

editor = "Hend Al-Khalifa and Tamer Elsayed and Hamdy Mubarak and Abdulmohsen Al-Thubaity and Walid Magdy and Kareem Darwish",

booktitle = "5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022",

}

Premasiri, D, Ranasinghe, T, Zaghouani, W & Mitkov, R 2022, DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain. in H Al-Khalifa, T Elsayed, H Mubarak, A Al-Thubaity, W Magdy & K Darwish (eds), 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022. 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022, European Language Resources Association (ELRA), pp. 88-95, 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022, Marseille, France, 20/06/22.

DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain. / Premasiri, Damith; Ranasinghe, Tharindu; Zaghouani, Wajdi et al.
5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022. ed. / Hend Al-Khalifa; Tamer Elsayed; Hamdy Mubarak; Abdulmohsen Al-Thubaity; Walid Magdy; Kareem Darwish. European Language Resources Association (ELRA), 2022. p. 88-95 (5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022).

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

TY - GEN

T1 - DTW at Qur’an QA 2022

T2 - 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022

AU - Premasiri, Damith

AU - Ranasinghe, Tharindu

AU - Zaghouani, Wajdi

AU - Mitkov, Ruslan

N1 - Publisher Copyright: © European Language Resources Association (ELRA).

PY - 2022

Y1 - 2022

N2 - The task of machine reading comprehension (MRC) is a useful benchmark to evaluate the natural language understanding of machines. It has gained popularity in the natural language processing (NLP) field mainly due to the large number of datasets released for many languages. However, the research in MRC has been understudied in several domains, including religious texts. The goal of the Qur’an QA 2022 shared task is to fill this gap by producing state-of-the-art question answering and reading comprehension research on Qur’an. This paper describes the DTW entry to the Quran QA 2022 shared task. Our methodology uses transfer learning to take advantage of available Arabic MRC data. We further improve the results using various ensemble learning strategies. Our approach provided a partial Reciprocal Rank (pRR) score of 0.49 on the test set, proving its strong performance on the task.

AB - The task of machine reading comprehension (MRC) is a useful benchmark to evaluate the natural language understanding of machines. It has gained popularity in the natural language processing (NLP) field mainly due to the large number of datasets released for many languages. However, the research in MRC has been understudied in several domains, including religious texts. The goal of the Qur’an QA 2022 shared task is to fill this gap by producing state-of-the-art question answering and reading comprehension research on Qur’an. This paper describes the DTW entry to the Quran QA 2022 shared task. Our methodology uses transfer learning to take advantage of available Arabic MRC data. We further improve the results using various ensemble learning strategies. Our approach provided a partial Reciprocal Rank (pRR) score of 0.49 on the test set, proving its strong performance on the task.

KW - Ensemble Learning

KW - Machine Reading Comprehension

KW - Qur’an

KW - Transfer Learning

KW - Transformers

UR - http://www.scopus.com/inward/record.url?scp=85136158390&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85136158390

T3 - 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022

SP - 88

EP - 95

BT - 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022

A2 - Al-Khalifa, Hend

A2 - Elsayed, Tamer

A2 - Mubarak, Hamdy

A2 - Al-Thubaity, Abdulmohsen

A2 - Magdy, Walid

A2 - Darwish, Kareem

PB - European Language Resources Association (ELRA)

Y2 - 20 June 2022 through 25 June 2022

ER -

Premasiri D, Ranasinghe T, Zaghouani W, Mitkov R. DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain. In Al-Khalifa H, Elsayed T, Mubarak H, Al-Thubaity A, Magdy W, Darwish K, editors, 5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022. European Language Resources Association (ELRA). 2022. p. 88-95. (5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022 - Proceedings at Language Resources and Evaluation Conference, LREC 2022).

DTW at Qur’an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain

Abstract

Publication series

Conference

Keywords

Other files and links

Fingerprint

Cite this