Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study

TL;DR

This empirical study investigates whether adding contextual data like type annotations and comments improves the performance of transformer-based code completion models, finding that removing type annotations can sometimes enhance model accuracy.

Contribution

The paper provides an empirical evaluation of the impact of contextual data on code completion models, highlighting counterintuitive results and offering guidance for model training and selection.

Findings

Models perform better without type annotations.

Multi-line comments improve model performance.

Small effect sizes indicate modest impact.

Abstract

Transformer-based pre-trained models have recently achieved great results in solving many software engineering tasks including automatic code completion which is a staple in a developer's toolkit. While many have striven to improve the code-understanding abilities of such models, the opposite -- making the code easier to understand -- has not been properly investigated. In this study, we aim to answer whether making code easier to understand through using contextual data improves the performance of pre-trained code language models for the task of code completion. We consider type annotations and comments as two common forms of additional contextual information that often help developers understand code better. For the experiments, we study code completion in two granularity levels; token and line completion and take three recent and large-scale language models for source code: UniXcoder, CodeGPT, and InCoder with five evaluation metrics. Finally, we perform the Wilcoxon Signed Rank test to gauge significance and measure the effect size. Contrary to our expectations, all models perform better if type annotations are removed (albeit the effect sizes are small). For comments, we find that the models perform better in the presence of multi-line comments (again with small effect sizes). Based on our observations, we recommend making proper design choices when training, fine-tuning, or simply selecting such models given the intended data and application. Better evaluations and multi-modal techniques can also be further investigated to improve the practicality and accuracy of auto-completions.