Improve Language Modelling for Code Completion through Statement Level Language Model based on Statement Embedding Generated by BiLSTM

TL;DR

This paper introduces a statement-level language model using BiLSTM and attention mechanisms to improve code completion accuracy, especially for long source code with many statements.

Contribution

The paper proposes a novel statement-level language model that captures long-term dependencies in source code using BiLSTM and attention, outperforming existing models.

Findings

Outperforms state-of-the-art models in token-level code completion

Effective in handling long source code with many statements

Demonstrates improved accuracy on inner-project and cross-project datasets

Abstract

Language models such as RNN, LSTM or other variants have been widely used as generative models in natural language processing. In last few years, taking source code as natural languages, parsing source code into a token sequence and using a language model such as LSTM to train that sequence are state-of-art methods to get a generative model for solving the problem of code completion. However, for source code with hundreds of statements, traditional LSTM model or attention-based LSTM model failed to capture the long term dependency of source code. In this paper, we propose a novel statement-level language model (SLM) which uses BiLSTM to generate the embedding for each statement. The standard LSTM is adopted in SLM to iterate and accumulate the embedding of each statement in context to help predict next code. The statement level attention mechanism is also adopted in the model. The proposed model SLM is aimed at token level code completion. The experiments on inner-project and cross-project data sets indicate that the newly proposed statement-level language model with attention mechanism (SLM) outperforms all other state-of-art models in token level code completion task.