COREQQA: a COmpliance REQuirements understanding using question answering tool

Sallam Abualhaija; Chetan Arora; Lionel C. Briand

doi:10.1145/3540250.3558926

COREQQA: a COmpliance REQuirements understanding using question answering tool

Sallam Abualhaija, Chetan Arora, Lionel C. Briand

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

1 Citation (Scopus)

Abstract

We introduce COREQQA, a tool for assisting requirements engineers in acquiring a better understanding of compliance requirements by means of automated Question Answering. Extracting compliance-related requirements by manually navigating through a legal document is both time-consuming and error-prone. COREQQA enables requirements engineers to pose questions in natural language about a compliance-related topic given some legal document, e.g., asking about data breach. The tool then automatically navigates through the legal document and returns to the requirements engineer a list of text passages containing the possible answers to the input question. For better readability, the tool also highlights the likely answers in these passages. The engineer can then use this output for specifying compliance requirements. COREQQA is developed using advanced large-scale language models from BERT's family. COREQQA has been evaluated on four legal documents. The results of this evaluation are briefly presented in the paper. The tool is publicly available on Zenodo (https://doi.org/10.5281/zenodo.6653514).

Original language	English
Title of host publication	Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering
Editors	Abhik Roychoudhury, Cristian Cadar, Miryung Kim
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Pages	1682-1686
Number of pages	5
ISBN (Electronic)	9781450394130
DOIs	https://doi.org/10.1145/3540250.3558926
Publication status	Published - 2022
Externally published	Yes
Event	Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2022 - Singapore, Singapore Duration: 14 Nov 2022 → 18 Nov 2022 Conference number: 30th https://dl.acm.org/doi/proceedings/10.1145/3540250 (Proceedings) https://2022.esec-fse.org (Website)

Conference

Conference	Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2022
Abbreviated title	ESEC/FSE 2022
Country/Territory	Singapore
City	Singapore
Period	14/11/22 → 18/11/22
Internet address	https://dl.acm.org/doi/proceedings/10.1145/3540250 (Proceedings) https://2022.esec-fse.org (Website)

Keywords

BERT
Language Models (LMs)
Natural Language Processing (NLP)
Question Answering
Regulatory Compliance
Requirements Engineering (RE)

Access to Document

10.1145/3540250.3558926

441462292-oaFinal published version, 235 KB

Cite this

Abualhaija, S., Arora, C., & Briand, L. C. (2022). COREQQA: a COmpliance REQuirements understanding using question answering tool. In A. Roychoudhury, C. Cadar, & M. Kim (Eds.), Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering (pp. 1682-1686). Association for Computing Machinery (ACM). https://doi.org/10.1145/3540250.3558926

Abualhaija, Sallam ; Arora, Chetan ; Briand, Lionel C. / COREQQA : a COmpliance REQuirements understanding using question answering tool. Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering. editor / Abhik Roychoudhury ; Cristian Cadar ; Miryung Kim. New York NY USA : Association for Computing Machinery (ACM), 2022. pp. 1682-1686

@inproceedings{5e8a8c0e0a394b659c282765cae071dc,

title = "COREQQA: a COmpliance REQuirements understanding using question answering tool",

abstract = "We introduce COREQQA, a tool for assisting requirements engineers in acquiring a better understanding of compliance requirements by means of automated Question Answering. Extracting compliance-related requirements by manually navigating through a legal document is both time-consuming and error-prone. COREQQA enables requirements engineers to pose questions in natural language about a compliance-related topic given some legal document, e.g., asking about data breach. The tool then automatically navigates through the legal document and returns to the requirements engineer a list of text passages containing the possible answers to the input question. For better readability, the tool also highlights the likely answers in these passages. The engineer can then use this output for specifying compliance requirements. COREQQA is developed using advanced large-scale language models from BERT's family. COREQQA has been evaluated on four legal documents. The results of this evaluation are briefly presented in the paper. The tool is publicly available on Zenodo (https://doi.org/10.5281/zenodo.6653514).",

keywords = "BERT, Language Models (LMs), Natural Language Processing (NLP), Question Answering, Regulatory Compliance, Requirements Engineering (RE)",

author = "Sallam Abualhaija and Chetan Arora and Briand, {Lionel C.}",

note = "Funding Information: This paper was supported by Central Legislative Service (SCL) {\'s} Government of Luxembourg, the Luxembourg National Research Fund (FNR) under grants PUBLIC2-17/IS/11801776, and by NSERC of Canada under the Discovery and CRC programs. Publisher Copyright: {\textcopyright} 2022 Owner/Author.; Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2022, ESEC/FSE 2022 ; Conference date: 14-11-2022 Through 18-11-2022",

year = "2022",

doi = "10.1145/3540250.3558926",

language = "English",

pages = "1682--1686",

editor = "Abhik Roychoudhury and Cristian Cadar and Miryung Kim",

booktitle = "Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

url = "https://dl.acm.org/doi/proceedings/10.1145/3540250, https://2022.esec-fse.org",

}

Abualhaija, S, Arora, C & Briand, LC 2022, COREQQA: a COmpliance REQuirements understanding using question answering tool. in A Roychoudhury, C Cadar & M Kim (eds), Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering. Association for Computing Machinery (ACM), New York NY USA, pp. 1682-1686, Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2022, Singapore, Singapore, 14/11/22. https://doi.org/10.1145/3540250.3558926

COREQQA : a COmpliance REQuirements understanding using question answering tool. / Abualhaija, Sallam; Arora, Chetan; Briand, Lionel C.

Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering. ed. / Abhik Roychoudhury; Cristian Cadar; Miryung Kim. New York NY USA : Association for Computing Machinery (ACM), 2022. p. 1682-1686.

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

TY - GEN

T1 - COREQQA

T2 - Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2022

AU - Abualhaija, Sallam

AU - Arora, Chetan

AU - Briand, Lionel C.

N1 - Conference code: 30th

PY - 2022

Y1 - 2022

N2 - We introduce COREQQA, a tool for assisting requirements engineers in acquiring a better understanding of compliance requirements by means of automated Question Answering. Extracting compliance-related requirements by manually navigating through a legal document is both time-consuming and error-prone. COREQQA enables requirements engineers to pose questions in natural language about a compliance-related topic given some legal document, e.g., asking about data breach. The tool then automatically navigates through the legal document and returns to the requirements engineer a list of text passages containing the possible answers to the input question. For better readability, the tool also highlights the likely answers in these passages. The engineer can then use this output for specifying compliance requirements. COREQQA is developed using advanced large-scale language models from BERT's family. COREQQA has been evaluated on four legal documents. The results of this evaluation are briefly presented in the paper. The tool is publicly available on Zenodo (https://doi.org/10.5281/zenodo.6653514).

AB - We introduce COREQQA, a tool for assisting requirements engineers in acquiring a better understanding of compliance requirements by means of automated Question Answering. Extracting compliance-related requirements by manually navigating through a legal document is both time-consuming and error-prone. COREQQA enables requirements engineers to pose questions in natural language about a compliance-related topic given some legal document, e.g., asking about data breach. The tool then automatically navigates through the legal document and returns to the requirements engineer a list of text passages containing the possible answers to the input question. For better readability, the tool also highlights the likely answers in these passages. The engineer can then use this output for specifying compliance requirements. COREQQA is developed using advanced large-scale language models from BERT's family. COREQQA has been evaluated on four legal documents. The results of this evaluation are briefly presented in the paper. The tool is publicly available on Zenodo (https://doi.org/10.5281/zenodo.6653514).

KW - BERT

KW - Language Models (LMs)

KW - Natural Language Processing (NLP)

KW - Question Answering

KW - Regulatory Compliance

KW - Requirements Engineering (RE)

UR - http://www.scopus.com/inward/record.url?scp=85143054512&partnerID=8YFLogxK

U2 - 10.1145/3540250.3558926

DO - 10.1145/3540250.3558926

M3 - Conference Paper

AN - SCOPUS:85143054512

SP - 1682

EP - 1686

BT - Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering

A2 - Roychoudhury, Abhik

A2 - Cadar, Cristian

A2 - Kim, Miryung

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

Y2 - 14 November 2022 through 18 November 2022

ER -

Abualhaija S, Arora C, Briand LC. COREQQA: a COmpliance REQuirements understanding using question answering tool. In Roychoudhury A, Cadar C, Kim M, editors, Proceedings of the 30th ACM Joint Meeting - European Software Engineering Conference and Symposium on the Foundations of Software Engineering. New York NY USA: Association for Computing Machinery (ACM). 2022. p. 1682-1686 https://doi.org/10.1145/3540250.3558926

COREQQA: a COmpliance REQuirements understanding using question answering tool

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this