Requirement Formalisation using Natural Language Processing and Machine Learning: A Systematic Review
This is an incremental survey that identifies challenges and future directions for researchers and practitioners in software engineering aiming to automate requirement formalization.
The paper conducted a systematic review of 47 studies from 2012 to 2022 on using Natural Language Processing and Machine Learning for Requirement Formalisation, finding that heuristic NLP approaches are most common and Deep Learning is underutilized, with a key challenge being the lack of standard benchmarks for performance comparison.
Improvement of software development methodologies attracts developers to automatic Requirement Formalisation (RF) in the Requirement Engineering (RE) field. The potential advantages by applying Natural Language Processing (NLP) and Machine Learning (ML) in reducing the ambiguity and incompleteness of requirement written in natural languages is reported in different studies. The goal of this paper is to survey and classify existing work on NLP and ML for RF, identifying 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 common 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, primary operating on structured and semi-structured data. This study also revealed that Deep Learning (DL) technique 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.