Paper published in a book (Scientific congresses, symposiums and conference proceedings)
Automated Handling of Anaphoric Ambiguity in Requirements: A Multi-solution Study
Ezzini, Saad; Abualhaija, Sallam; Arora, Chetan et al.
2022In Proceedings of the 44th International Conference on Software Engineering (ICSE'22), Pittsburgh, PA, USA 22-27 May 2022
Peer reviewed
 

Files


Full Text
icse22-main-1094.pdf
Author preprint (1.15 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Requirements Engineering; Natural-language Requirements; Ambiguity; Natural Language Processing (NLP); Machine Learning (ML); Language Models; BERT
Abstract :
[en] Ambiguity is a pervasive issue in natural-language requirements. A common source of ambiguity in requirements is when a pronoun is anaphoric. In requirements engineering, anaphoric ambiguity occurs when a pronoun can plausibly refer to different entities and thus be interpreted differently by different readers. In this paper, we develop an accurate and practical automated approach for handling anaphoric ambiguity in requirements, addressing both ambiguity detection and anaphora interpretation. In view of the multiple competing natural language processing (NLP) and machine learning (ML) technologies that one can utilize, we simultaneously pursue six alternative solutions, empirically assessing each using a collection of ~1,350 industrial requirements. The alternative solution strategies that we consider are natural choices induced by the existing technologies; these choices frequently arise in other automation tasks involving natural-language requirements. A side-by-side empirical examination of these choices helps develop insights about the usefulness of different state-of-the-art NLP and ML technologies for addressing requirements engineering problems. For the ambiguity detection task, we observe that supervised ML outperforms both a large-scale language model, SpanBERT (a variant of BERT), as well as a solution assembled from off-the-shelf NLP coreference resolvers. In contrast, for anaphora interpretation, SpanBERT yields the most accurate solution. In our evaluation, (1) the best solution for anaphoric ambiguity detection has an average precision of ~60% and a recall of 100%, and (2) the best solution for anaphora interpretation (resolution) has an average success rate of ~98%.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SVV - Software Verification and Validation
Disciplines :
Computer science
Author, co-author :
Ezzini, Saad ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SVV
Abualhaija, Sallam  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SVV
Arora, Chetan
Sabetzadeh, Mehrdad
External co-authors :
yes
Language :
English
Title :
Automated Handling of Anaphoric Ambiguity in Requirements: A Multi-solution Study
Publication date :
May 2022
Event name :
44th International Conference on Software Engineering
Event date :
from 22-05-2022 to 27-05-2022
Main work title :
Proceedings of the 44th International Conference on Software Engineering (ICSE'22), Pittsburgh, PA, USA 22-27 May 2022
Publisher :
Association for Computing Machinery
Peer reviewed :
Peer reviewed
FnR Project :
FNR12632261 - Early Quality Assurance Of Critical Systems, 2018 (01/01/2019-31/12/2021) - Mehrdad Sabetzadeh
Funders :
FNR - Luxembourg National Research Fund [LU]
Available on ORBilu :
since 07 February 2022

Statistics


Number of views
560 (51 by Unilu)
Number of downloads
755 (28 by Unilu)

Scopus citations®
 
11
Scopus citations®
without self-citations
7
OpenCitations
 
6

Bibliography


Similar publications



Contact ORBilu