Application of reinforcement learning to requirements engineering: Requirements tracing

Hakim Sultanov; Jane Huffman Hayes

doi:10.1109/RE.2013.6636705

Application of reinforcement learning to requirements engineering: Requirements tracing

Hakim Sultanov, Jane Huffman Hayes

Computer Science

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

32 Scopus citations

Abstract

We posit that machine learning can be applied to effectively address requirements engineering problems. Specifically, we present a requirements traceability method based on the machine learning technique Reinforcement Learning (RL). The RL method demonstrates a rather targeted generation of candidate links between textual requirements artifacts (high level requirements traced to low level requirements, for example). The technique has been validated using two real-world datasets from two problem domains. Our technique demonstrated statistically significant better results than the Information Retrieval technique.

Original language	English
Title of host publication	2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings
Pages	52-61
Number of pages	10
DOIs	https://doi.org/10.1109/RE.2013.6636705
State	Published - 2013
Event	2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Rio de Janeiro, Brazil Duration: Jul 15 2013 → Jul 19 2013

Publication series

Name	2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings

Conference

Conference	2013 21st IEEE International Requirements Engineering Conference, RE 2013
Country/Territory	Brazil
City	Rio de Janeiro
Period	7/15/13 → 7/19/13

Keywords

Information retrieval
Machine learning
Reinforcement learning
Requirements traceability
Research Project 2 of Grand Challenges of Traceability
Software engineering
Ubiquitous Grand Challenge

ASJC Scopus subject areas

Software

Access to Document

10.1109/RE.2013.6636705

Cite this

Sultanov, H., & Hayes, J. H. (2013). Application of reinforcement learning to requirements engineering: Requirements tracing. In 2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings (pp. 52-61). Article 6636705 (2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings). https://doi.org/10.1109/RE.2013.6636705

@inproceedings{c578d53dca0e42fbb2560d1318514a79,

title = "Application of reinforcement learning to requirements engineering: Requirements tracing",

abstract = "We posit that machine learning can be applied to effectively address requirements engineering problems. Specifically, we present a requirements traceability method based on the machine learning technique Reinforcement Learning (RL). The RL method demonstrates a rather targeted generation of candidate links between textual requirements artifacts (high level requirements traced to low level requirements, for example). The technique has been validated using two real-world datasets from two problem domains. Our technique demonstrated statistically significant better results than the Information Retrieval technique.",

keywords = "Information retrieval, Machine learning, Reinforcement learning, Requirements traceability, Research Project 2 of Grand Challenges of Traceability, Software engineering, Ubiquitous Grand Challenge",

author = "Hakim Sultanov and Hayes, {Jane Huffman}",

year = "2013",

doi = "10.1109/RE.2013.6636705",

language = "English",

isbn = "9781467357654",

series = "2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings",

pages = "52--61",

booktitle = "2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings",

note = "2013 21st IEEE International Requirements Engineering Conference, RE 2013 ; Conference date: 15-07-2013 Through 19-07-2013",

}

Sultanov, H & Hayes, JH 2013, Application of reinforcement learning to requirements engineering: Requirements tracing. in 2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings., 6636705, 2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings, pp. 52-61, 2013 21st IEEE International Requirements Engineering Conference, RE 2013, Rio de Janeiro, Brazil, 7/15/13. https://doi.org/10.1109/RE.2013.6636705

Application of reinforcement learning to requirements engineering: Requirements tracing. / Sultanov, Hakim; Hayes, Jane Huffman.
2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings. 2013. p. 52-61 6636705 (2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings).

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

TY - GEN

T1 - Application of reinforcement learning to requirements engineering

T2 - 2013 21st IEEE International Requirements Engineering Conference, RE 2013

AU - Sultanov, Hakim

AU - Hayes, Jane Huffman

PY - 2013

Y1 - 2013

N2 - We posit that machine learning can be applied to effectively address requirements engineering problems. Specifically, we present a requirements traceability method based on the machine learning technique Reinforcement Learning (RL). The RL method demonstrates a rather targeted generation of candidate links between textual requirements artifacts (high level requirements traced to low level requirements, for example). The technique has been validated using two real-world datasets from two problem domains. Our technique demonstrated statistically significant better results than the Information Retrieval technique.

AB - We posit that machine learning can be applied to effectively address requirements engineering problems. Specifically, we present a requirements traceability method based on the machine learning technique Reinforcement Learning (RL). The RL method demonstrates a rather targeted generation of candidate links between textual requirements artifacts (high level requirements traced to low level requirements, for example). The technique has been validated using two real-world datasets from two problem domains. Our technique demonstrated statistically significant better results than the Information Retrieval technique.

KW - Information retrieval

KW - Machine learning

KW - Reinforcement learning

KW - Requirements traceability

KW - Research Project 2 of Grand Challenges of Traceability

KW - Software engineering

KW - Ubiquitous Grand Challenge

UR - http://www.scopus.com/inward/record.url?scp=84891083117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891083117&partnerID=8YFLogxK

U2 - 10.1109/RE.2013.6636705

DO - 10.1109/RE.2013.6636705

M3 - Conference contribution

AN - SCOPUS:84891083117

SN - 9781467357654

T3 - 2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings

SP - 52

EP - 61

BT - 2013 21st IEEE International Requirements Engineering Conference, RE 2013 - Proceedings

Y2 - 15 July 2013 through 19 July 2013

ER -

Application of reinforcement learning to requirements engineering: Requirements tracing

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this