Premkumar T. Devanbu

Abstract Programming languages, like their “natural” counterparts, are rich, powerful and expressive. But while skilled writers like Zadie Smith, Umberto Eco, and Salman Rushdie delight us with their elegant, creative deployment of the power and beauty of natural language, most of what us oridinary 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. We will argue that in fact, despite the power and expressiveness of programming languages, most, in fact are quite repetitive and predictable, and can be fruitfully modeled using the same types of statistical models used in natural language processing. There are numerous and exciting applications of this rather unexpected finding. This insight has led to an international effort, with numerous projects in the US, Canada, UK, Switzerland, and elsewhere. Many interesting results have been obtained. This tutorial is a practitioners’ introduction to the basic concepts of Statistical Natural Language Processing, and current results, for Software Engineering Researchers who want to learn about this exciting.

Speaker's Bio Prem Devanbu received his B.Tech from the Indian Institute of Technology in Chennai, India and his PhD from Rutgers University. He is Professor of Computer Science at UC Davis. He has published over 140 papers. He has served as program chair for both major conferences (ICSE and FSE) and served on the editorial boards of all major journals (IEEE TSE, ACM TOSEM, ESE Journal) in software engineering. He has received 3 best paper awards (MSR, ASE, ICSE NIER) and 4 ACM Distinguished Paper awards, and the MSR 2016 10 year most-influential paper award. His papers have appeared by invitation in CACM Research Highlights twice, in 2009 and in 2016. His former students and postdocs have held faculty positions at CMU, U. of Virginia, UCL (London, UK), U of Alberta, UBC (Vancouver) and Microsoft Research. He even has his own web page, which Google seems to know about.