Thu 7 Sep 2023 11:15 - 11:45 at f142 - AI & GPT Chair(s): Mehrdad Sabetzadeh

Named entity recognition (NER) is a natural language processing task that has been used in Requirements Engineering for the identification of entities such as actors, actions, operators, resources, events, GUI elements, hardware, APIs, and others. NER might be particularly useful for extracting key information from Software Requirements Specification documents, which provide a blueprint for software development. However, a common challenge in this domain is the lack of annotated data. In this article, we propose and analyze two zero-shot approaches for NER in the requirements engineering domain. These are found to be particularly effective in situations where labeled data is scarce or non-existent. The first approach is a template-based zero-shot learning mechanism that uses the prompt engineering approach and achieves 93% accuracy according to our experimental results. The second solution takes an orthogonal approach by transforming the entity recognition problem into a question-answering task which results in 98% accuracy. Both zero-shot NER approaches introduced in this work perform better than the existing state-of-the-art solutions in the requirements engineering domain.

Thu 7 Sep

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

10:45 - 12:15
AI & GPTResearch Papers / RE@Next! Papers at f142
Chair(s): Mehrdad Sabetzadeh University of Ottawa
10:45
30m
Paper
Prompting Creative Requirements via Traceable and Adversarial Examples in Deep LearningArtifact Available
Research Papers
A: Hemanth Gudaparthi Governors State University, A: Nan Niu University of Cincinnati, A: Boyang Wang University of Cincinnati, A: Tanmay Bhowmik Mississippi State University, A: Hui Liu Beijing Institute of Technology, A: Jianzhang Zhang , A: Juha Savolainen Danfoss, A: Glen Horton University of Cincinnati, A: Sean Crowe University of Cincinnati, A: Thomas Scherz University of Cincinnati, A: Lisa Haitz University of Cincinnati
11:15
30m
Paper
Zero-shot Learning for Named Entity Recognition in Software Specification DocumentsArtifact Available
Research Papers
A: Souvick Das , A: Novarun Deb Assistant Professor, Indian Institute of Information Technology, Vadodara, A: Agostino Cortesi Ca’ Foscari University of Venice, A: Nabendu Chaki
11:45
30m
Paper
Inconsistency Detection in Natural Language Requirements using ChatGPT: a Preliminary Evaluation}
RE@Next! Papers
A: Alessandro Fantechi University of Florence, A: Stefania Gnesi Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" , A: Lucia Passaro University of Pisa, A: Laura Semini Università di Pisa - Dipartimento di Informatica
File Attached