Title :
Fast and Precise Statistical Code Completion
Author_Institution :
ETH Zurich, Zurich, Switzerland
Abstract :
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.
Keywords :
application program interfaces; programming languages; statistical analysis; API code completion; N-gram language model; beam search; completion algorithm; experimental evaluation; smoothing methods; statistical code completion; Computational modeling; Libraries; Probability; Real-time systems; Runtime; Semantics; Smoothing methods; APIs; Code Completion; Statistical Language Models; Synthesis;
Conference_Titel :
Software Engineering (ICSE), 2015 IEEE/ACM 37th IEEE International Conference on
Conference_Location :
Florence
DOI :
10.1109/ICSE.2015.240
