ACM SIGSOFT Webinar: Deep Learning & Software Engineering - A Retrospective and Paths Forward

Title: ACM SIGSOFT Webinar: Deep Learning & Software Engineering - A Retrospective and Paths Forward
Kevin Moran
Date: July 14, 2021

ABSTRACT
Bridging the abstraction gap between concepts and source code is the essence of Software Engineering (SE). SE researchers regularly use machine learning to bridge this gap, but there are two fundamental issues with traditional applications of machine learning in SE research. Traditional applications are typically reliant on human intuition, and they are not capable of learning expressive yet efficient internal representations. Ultimately, SE research needs approaches that can automatically learn representations of massive, heterogeneous, datasets in situ, apply the learned features to a particular task, and possibly transfer knowledge from task to task.

Improvements in both computational power and the amount of memory in modern computer architectures have enabled new approaches to canonical machine learning tasks. Specifically, these architectural advances have enabled machines that are capable of learning deep, compositional representations of massive data depots. This rise of deep learning has led to tremendous advances in several fields. Given the complexity of software repositories and the artifacts therein, deep learning has ushered in new analytical frameworks and methodologies for SE research and its corresponding practical applications. A recent report from the 2019 NSF Workshop on Deep Learning & Software Engineering has referred to this area of research as Deep Learning for Software Engineering (DL4SE).

This talk will provide a retrospective on the current state of DL4SE research by offering an analysis on work that has been done across different software engineering tasks including code suggestion, program repair, and program synthesis, to name a few. Additionally, the talk will explore how different types of software artifacts and deep learning architectures have been used, as well as some pressing challenges faced by this line of work. The talk will conclude with a discussion of promising future directions of work as well as an overview of potential opportunities for the DL4SE research community to continue to drive impactful, open, and reproducible work.

SPEAKER
Kevin Moran

MODERATOR
Michele Tufano