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

doi:10.48550/arXiv.2205.06025

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

Research output: Chapter in Book/Published conference output › Conference publication

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. © 2022, CC BY.

Original language	English
Title of host publication	Proceedings of the OSACT 2022 Workshop @LREC2022
Number of pages	8
DOIs	https://doi.org/10.48550/arXiv.2205.06025
Publication status	Published - 12 May 2022

Bibliographical note

Access to Document

10.48550/arXiv.2205.06025Licence: CC BY 4.0

Premasirietal_2022_PP
Copyright 2022 with a Creative Commons Attribution 4.0 International (CC BY 4.0) license
Final published version, 279 KBLicence: CC BY 4.0

Cite this

@inproceedings{eb4d8f2278a743d18a9187999157928c,

title = "DTW at Qur'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'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. {\textcopyright} 2022, CC BY.",

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

year = "2022",

month = may,

day = "12",

doi = "10.48550/arXiv.2205.06025",

language = "English",

booktitle = "Proceedings of the OSACT 2022 Workshop @LREC2022",

}

TY - GEN

T1 - DTW at Qur'an QA 2022: Utilising Transfer Learning with Transformers for Question Answering in a Low-resource Domain

AU - Premasiri, Damith

AU - Ranasinghe, Tharindu

AU - Zaghouani, Wajdi

AU - Mitkov, Ruslan

PY - 2022/5/12

Y1 - 2022/5/12

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. © 2022, CC BY.

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. © 2022, CC BY.

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85130430331&partnerID=MN8TOARS

UR - https://arxiv.org/abs/2205.06025

U2 - 10.48550/arXiv.2205.06025

DO - 10.48550/arXiv.2205.06025

M3 - Conference publication

BT - Proceedings of the OSACT 2022 Workshop @LREC2022

ER -

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

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this