Natural language models for predicting programming comments

Statistical language models have success-fully been used to describe and analyze natural language documents. Recent work applying language models to program-ming languages is focused on the task of predicting code, while mainly ignoring the prediction of programmer comments. In this work, we predict comments from JAVA source files of open source projects, using topic models and n-grams, and we analyze the performance of the models given varying amounts of background data on the project being predicted. We evalu-ate models on their comment-completio