# Combining Program Analysis and Statistical Language Model for Code Statement Completion

arXiv: https://arxiv.org/abs/1911.07781 · HTML: https://mlsanity.com/paper/1911.07781/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2019.

## Built on by (most cited first, 5 of 5)

- [CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences](https://mlsanity.com/paper/2202.06689/) (2022)
- [Correctness Assessment of Code Generated by Large Language Models Using Internal Representations](https://mlsanity.com/paper/2501.12934/) (2025)
- [RAMBO: Enhancing RAG-based Repository-Level Method Body Completion](https://mlsanity.com/paper/2409.15204/) (2024)
- [Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study](https://mlsanity.com/paper/2304.12269/) (2023)
- [ARIST: An Effective API Argument Recommendation Approach](https://mlsanity.com/paper/2306.06620/) (2023)

## Abstract (arXiv)

Automatic code completion helps improve developers' productivity in their programming tasks. A program contains instructions expressed via code statements, which are considered as the basic units of program execution. In this paper, we introduce AutoSC, which combines program analysis and the principle of software naturalness to fill in a partially completed statement. AutoSC benefits from the strengths of both directions, in which the completed code statement is both frequent and valid. AutoSC is first trained on a large code corpus to derive the templates of candidate statements. Then, it uses program analysis to validate and concretize the templates into syntactically and type-valid candidate statements. Finally, these candidates are ranked by using a language model trained on the lexical form of the source code in the code corpus. Our empirical evaluation on the large datasets of real-world projects shows that AutoSC achieves 38.9-41.3% top-1 accuracy and 48.2-50.1% top-5 accuracy in statement completion. It also outperforms a state-of-the-art approach from 9X-69X in top-1 accuracy.