When Natural Language Processing jumps into Software Engineering
Dr Fabian Gilson
Computer Science & Software Engineering, University of Canterbury
Time & Place
Mon, 03 Aug 2020 15:00:00 NZST in Rm 105, Beatrice Tinsley Building
Software engineering is an intrinsically collaborative activity, especially in the era of Agile Software Development. Many actors are partaking in development activities, so that a common understanding should be reached at numerous stages during the overall development life-cycle. For a few years now, Natural Language Processing techniques have been employed either to extract key information from free-form text or to generate models from the analysis of text in order to ease the sharing of knowledge across all parties. A significant part of these
approaches focuses on retrieving lost domain and architectural knowledge through the analysis of documents, issue management systems or other forms of knowledge management systems. However, these post-processing methods are time-consuming by nature since they require to invest significant resources into the validation of the extracted knowledge. In this talk, we investigate how just-in-time "information" retrieval and model generation may help software engineers and stakeholders to capture design knowledge or increase their understanding of a software product under development.
Fabian graduated with a Master Degree in Computer Science at the University of Namur (Belgium) in 2005. He spent a couple of years in the industry as a software developer and analyst, then worked as a teaching assistant, a post-doctoral researcher and assistant lecturer at the University of Namur before being appointed lecturer at the University of Canterbury in 2017. Fabian’s research aims at bridging machine learning techniques and Agile software development practices. His current projects include approaches to (collaboratively) generate models from user stories (i.e. natural language descriptions), extract design decisions from chat-based communication, improving the management of technical debt with architecture-level metrics. Fabian is also active into enhancing the teaching and learning of software and model-driven engineering (including software language engineering) through evidence-based research and teaching.