Code completion with statistical language models
Veselin Raychev, Martin Vechev, Eran Yahav · Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation · 2014
We address the problem of synthesizing code completions for programs using APIs. Given a program with holes, we synthesize completions for holes with the most likely sequences of method calls.
Cited by 538 works. doi:10.1145/2594291.2594321
Authors
References
- Finding Structure in Time
- Estimation of probabilities from sparse data for the language model component of a speech recognizer
- SRILM - an extensible language modeling toolkit
- A neural probabilistic language model
- Improved backing-off for M-gram language modeling
- Strategies for training large scale neural network language models
- The zero-frequency problem: estimating the probabilities of novel events in adaptive text compression
- Points-to analysis in almost linear time
- Discovering models of software processes from event-based data
- Two decades of statistical language modeling: where do we go from here?