Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review

TY - GEN

T1 - Requirement Formalisation Using Natural Language Processing and Machine Learning: A Systematic Review

AU - Rahimi, Shekoufeh

AU - Lano, Kevin Charles

AU - Lin, Chenghua

PY - 2022/12/22

Y1 - 2022/12/22

N2 - Improvement of software development methodologies attracts developers to automatic Requirement Formalisation (RF) in the Requirement Engineering (RE) field. The potential advantages of applying Natural Language Processing (NLP) and Machine Learning (ML) in reducing the ambiguity and incompleteness of requirements written in natural languages are reported in different studies. The goal of this paper is to survey and classify existing works on NLP and ML for RF, identifying the challenges in this domain and providing promising future research directions. To achieve this, we conducted a systematic literature review to outline the current state-of-the-art of NLP and ML techniques in RF by selecting 257 papers from commonly used libraries. The search result is filtered by defining inclusion and exclusion criteria and 47 relevant studies between 2012 and 2022 are selected. We found that heuristic NLP approaches are the most common NLP techniques used for automatic RF, primarily operating on structured and semi-structured data. This study also revealed that Deep Learning (DL) techniques are not widely used, instead, classical ML techniques are predominant in the surveyed studies. More importantly, we identified the difficulty of comparing the performance of different approaches due to the lack of standard benchmark cases for RF.

AB - Improvement of software development methodologies attracts developers to automatic Requirement Formalisation (RF) in the Requirement Engineering (RE) field. The potential advantages of applying Natural Language Processing (NLP) and Machine Learning (ML) in reducing the ambiguity and incompleteness of requirements written in natural languages are reported in different studies. The goal of this paper is to survey and classify existing works on NLP and ML for RF, identifying the challenges in this domain and providing promising future research directions. To achieve this, we conducted a systematic literature review to outline the current state-of-the-art of NLP and ML techniques in RF by selecting 257 papers from commonly used libraries. The search result is filtered by defining inclusion and exclusion criteria and 47 relevant studies between 2012 and 2022 are selected. We found that heuristic NLP approaches are the most common NLP techniques used for automatic RF, primarily operating on structured and semi-structured data. This study also revealed that Deep Learning (DL) techniques are not widely used, instead, classical ML techniques are predominant in the surveyed studies. More importantly, we identified the difficulty of comparing the performance of different approaches due to the lack of standard benchmark cases for RF.

M3 - Conference contribution

SP - 1

EP - 8

BT - SCITEPRESS Digital Library

PB - SCITEPRESS Digital Library

T2 - International conference on Model-Based Software and Systems Engineering

Y2 - 19 February 2023 through 21 February 2023

ER -