Naturalness and Bimodality of Code: A Research Overview
While natural languages are rich in vocabulary and grammatical flexibility, most human are mundane and repetitive. This repetitiveness in natural language has led to great advances in statistical NLP methods. At UC Davis, we discovered (a decade ago) that, despite the considerable power and flexibility of programming languages, large software corpora are actually even more repetitive than NL Corpora. We went on to show that this “naturalness” of code could be captured in statistical models, and exploited within software tools. This line of work enjoyed a tremendous boost from the high-capacity and flexibility of deep learning models. Numerous other creative and interesting applications of naturalness have ensued, from colleagues around the world. More recently, we have focused on another property of software: it is bimodal. Software is written not only to be run on machines, but also read by humans; this makes it amenable to both formal analysis, and statistical prediction. Bimodality allows new ways of training machine learning models, new ways of designing analysis algorithms, and new ways to understand the practice of programming. In this talk, I will present an overview of “Naturalness” studies, and the promise of bimodality.

Prem Devanbu is Distinguished Professor (eff. July 1) of Computer Science at UC Davis. He received his B.Tech from IIT Madras, and his Ph.D from Rutgers University under Alex Borgida. After a career in Industrial R&D at Bell Labs in New Jersey, he joined UC Davis. He has worked in several areas, including Software tools, Secure Data Outsourcing, Empirical Software Engineering, and the Naturalness of Software, and applications thereof.