Prem Devanbu

On the Naturalness of Software, and how to exploit it for Fun and Profit.

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 oridnary 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 is <> 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 Engineers who want to learn about this exciting and rapidly developing area.

Speaker's Bio
Prem Devanbu received his B.Tech from the Indian Institute of Technology in Chennai, India, before you were born, and his PhD from Rutgers University in 1994. After spending nearly 20 years at Bell Labs and its various offshoots, he escaped New Jersey traffic to join the CS faculty at UC Davis in late 1997. For almost a decade now, he has been working at ways to exploit the copious amounts of available open-source project data to bring more joy, meaning, and fulfillment to the lives of programmers.