Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Requirement or Not, That is the Question: A Case from the Railway Industry
RISE Research Institutes of Sweden, Digitala system, Industriella system. Mälardalen University, Sweden.ORCID-id: 0009-0006-8512-6412
RISE Research Institutes of Sweden, Digitala system, Industriella system. Mälardalen University, Sweden.ORCID-id: 0000-0001-6418-9971
RISE Research Institutes of Sweden, Digitala system, Industriella system.ORCID-id: 0000-0002-1512-0844
Mälardalen University, Sweden.
Vise andre og tillknytning
2023 (engelsk)Inngår i: Lecture Notes in Computer Science. Volume 13975. Pages 105 - 121 2023, Springer Science and Business Media Deutschland GmbH , 2023, s. 105-121Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Requirements in tender documents are often mixed with other supporting information. Identifying requirements in large tender documents could aid the bidding process and help estimate the risk associated with the project.  Manual identification of requirements in large documents is a resource-intensive activity that is prone to human error and limits scalability. This study compares various state-of-the-art approaches for requirements identification in an industrial context. For generalizability, we also present an evaluation on a real-world public dataset. We formulate the requirement identification problem as a binary text classification problem. Various state-of-the-art classifiers based on traditional machine learning, deep learning, and few-shot learning are evaluated for requirements identification based on accuracy, precision, recall, and F1 score. Results from the evaluation show that the transformer-based BERT classifier performs the best, with an average F1 score of 0.82 and 0.87 on industrial and public datasets, respectively. Our results also confirm that few-shot classifiers can achieve comparable results with an average F1 score of 0.76 on significantly lower samples, i.e., only 20% of the data.  There is little empirical evidence on the use of large language models and few-shots classifiers for requirements identification. This paper fills this gap by presenting an industrial empirical evaluation of the state-of-the-art approaches for requirements identification in large tender documents. We also provide a running tool and a replication package for further experimentation to support future research in this area. © 2023, The Author(s)

sted, utgiver, år, opplag, sider
Springer Science and Business Media Deutschland GmbH , 2023. s. 105-121
Emneord [en]
NLP, Requirements classification, Requirements identification, tender documents, Deep learning, Information retrieval systems, Natural language processing systems, Requirements engineering, Risk perception, Text processing, Bidding process, F1 scores, Human errors, Manual identification, Public dataset, Railway industry, Requirement identification, Requirements classifications, State-of-the-art approach, Classification (of information)
HSV kategori
Identifikatorer
URN: urn:nbn:se:ri:diva-64397DOI: 10.1007/978-3-031-29786-1_8Scopus ID: 2-s2.0-85152587069ISBN: 9783031297854 (tryckt)OAI: oai:DiVA.org:ri-64397DiVA, id: diva2:1755564
Konferanse
29th International Working Conference on Requirements Engineering: Foundation for Software Quality, REFSQ 2023. Barcelona, Spain. 17 April 2023 through 20 April 2023
Merknad

Correspondence Address: Abbas, M. RISE Research Institutes of Sweden, Sweden; email: muhammad.abbas@ri.se; Funding details: ITEA; Funding text 1: Acknowledgement. This work is partially funded by the AIDOaRt (KDT) and SmartDelta [27] (ITEA) projects.

Tilgjengelig fra: 2023-05-08 Laget: 2023-05-08 Sist oppdatert: 2023-11-03bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Bashir, SarmadAbbas, MuhammadSaadatmand, Mehrdad

Søk i DiVA

Av forfatter/redaktør
Bashir, SarmadAbbas, MuhammadSaadatmand, Mehrdad
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 47 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
v. 2.43.0