Fast and Precise Statistical Code Completion
Pascal Roos · 2015
The main problem we try to solve is API code completion which is both precise and works in real-time. We describe an efficient implementation of an N-gram language model combined with several smoothing methods and a completion algorithm based on beam search. We show that our system is both fast and precise using a thorough experimental evaluation. With optimal parameters we are able to find completions in milliseconds and the desired completion is in the top 3 suggestions in 89% of the time.