Seminar on NLP and ML for Mining Software Repositories by Dr. Treude on Feb 2nd

We arrange a seminar on Natural Language Processing and Machine Learning for Mining Software Repositories by Dr. Christoph Treude (University of Adelaide) on Feb 2nd 10:00-11:30am. Everyone is welcome!

Date: Feb 2nd FRI 10:00-11:30am
Location: Room 0526, Building 63, Nishi-Waseda campus

10:00-11:00 (incl. discussions)
Title: Using NLP and ML to unlock information hidden in software repositories
Talker: Christoph Treude (University of Adelaide)

Knowledge management plays a central role in many software development organizations. While much of the important technical knowledge can be captured in software artifacts, there often exists a gap between the information needs of software developers and the structure of this information in a repository. To help developers access information in their repositories more effectively, we are developing approaches to analyze and repackage these artifacts into formats that are more amenable to their readers. This talk will highlight several such approaches that we have developed and evaluated to support the various stakeholders in a software engineering project, including a task-based search interface for software documentation, a code snippet content assist to import code fragments from Stack Overflow, a machine learning approach to augment API documentation with “insight sentences”, and a portal designed to help project newcomers. Our work suggests that while much of the knowledge needed by software developers is already available somewhere in a repository, much work is needed to get it to developers in the right format when and where they need it.

Christoph Treude is an ARC DECRA Fellow and a Senior Lecturer in the School of Computer Science at the University of Adelaide, Australia and currently visiting the Nara Institute of Science and Technology in Japan on a JSPS fellowship. He completed his PhD in Computer Science at the University of Victoria, Canada, in 2012 and received his Diplom degree in Computer Science / Management Information Systems from the University of Siegen, Germany, in 2007. The goal of his research is to advance collaborative software engineering through empirical studies and the innovation of processes and tools that explicitly take the wide variety of artifacts available in a software repository into account.

11:00-11:30 Open discussions with some research introductions (if necessary)

Contact: Prof. Hironori Washizaki washizaki [at]