On the Naturalness of Software


Event Details
Thursday, January 16, 2014
Talk:
4:00 p.m., Avery 115

Reception:
3:30 p.m., Avery 348

Prem Devanbu, Ph.D. - Distinguished Speaker

Professor, University of California-Davis

Abstract

Programming languages, like their "natural" counterparts, are rich, powerful and expressive.  But while skilled writers like Zadie Smith, Shakespeare, and Rushdie delight us with their elegant, creative deployment of the power and beauty of English, most of what us regular mortals say and write everyday is very repetitive and highly predictable.

This predictability, as most of us have learned by now, is at the heart of the modern statistical revolution in speech recognition, natural language translation, question answering, etc.  I will argue that in fact, despite the power and expressiveness of programming languages, most software in fact is also quite repetitive and predictable, and can be fruitfully modeled using the same types of statistical models used in natural language processing.  I present some practical applications of this rather unexpected finding, and present a research vision arguing that this phenomenon is potentially rich in both scientific questions, and engineering promise.

PROJECT HISTORY: This international effort is currently funded by the U.S. NSF and the U.K. EPSRC.  Active collaborators include Zhendong Su at UC Davis, Roni Rosenfeld and William Cohen at CMU, Earl Barr and Mark Harman at University College, London, Abram Hindle at University of Alberta, Yuriy Brun at UMass Amherst, and Charles Sutton (UMass Amherst CS Ph.D. alum) of University of Edinburgh.  Related work is going on at Iowa State and Concordia Universities.  There's a lot to do, and we welcome more collaborators.

Speaker Bio

Prem Devanbu received his B.Tech from IIT Madras,  in Chennai, India, and his PhD from Rutgers University.  After spending nearly 20 years as both a developer and a researcher at Bell Labs and its various offshoots, he left Industry to join the CS faculty at UC Davis in late 1997, where he is now Professor of Computer Science.