Fantechi A., Gnesi S., Semini L.
Ambiguity detection in requirements ChatGPT Rule-based NLP tools
With the rapid advances of AI-based tools, the question of whether to use such tools or conventional rule-based tools often arises in many application domains. In this paper, we address this question when considering the issue of ambiguity in requirements documents. For this purpose, we consider GPT-3 that is the third-generation of the Generative Pretrained Transformer language model, developed by OpenAI and we compare its ambiguity detection capability with that of a publicly available rule-based NLP tool on a few example requirements documents.
Source: REFSQ 2023 - 29th International Working Conference on Requirement Engineering: Foundation for Software Quality: Posters and Tools, Barcelona, Spain, 17-20/04/2023
Publisher: M. Jeusfeld c/o Redaktion Sun SITE, Informatik V, RWTH Aachen., Aachen, Germania
@inproceedings{oai:it.cnr:prodotti:482040, title = {Rule-based NLP vs ChatGPT in ambiguity detection, a preliminary study}, author = {Fantechi A. and Gnesi S. and Semini L.}, publisher = {M. Jeusfeld c/o Redaktion Sun SITE, Informatik V, RWTH Aachen., Aachen, Germania}, booktitle = {REFSQ 2023 - 29th International Working Conference on Requirement Engineering: Foundation for Software Quality: Posters and Tools, Barcelona, Spain, 17-20/04/2023}, year = {2023} }