BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Understanding Source Code using Natural Language and Graph Neural 
 Networks - Miltos Allamanis\, Microsoft Research
DTSTART:20190215T120000Z
DTEND:20190215T130000Z
UID:TALK113401@talks.cam.ac.uk
CONTACT:Andrew Caines
DESCRIPTION:While computers are becoming an integral part of our lives\, p
 rogramming them still remains a highly specialized skill. The last few yea
 rs there is an increased research interest in methods that focus on the in
 tersection of programming and natural language processing (NLP)\, that aim
  to help create machine learning-based tools that aid software engineers b
 y “understanding” source code’s natural language components and allo
 w end-users to employ natural language to interact with computers.\n \nWit
 hin this research area\, Graph Neural Networks (GNN) have shown promising 
 results in exploiting the rich structure and long-range dependencies in so
 urce code. In this talk\, I will discuss three machine learning architectu
 res that employ GNNs for source code-related tasks including bug detection
 \, code summarization and code generation. Then\, I will illustrate how th
 ese networks can find applications in NLP tasks\, such as summarization.  
 Finally\, I will conclude with a discussion of some of the open challenges
  on source code-related tasks and potential\nconnections to NLP.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR