# Learning Python Code Suggestion with a Sparse Pointer Network

arXiv: https://arxiv.org/abs/1611.08307 · HTML: https://mlsanity.com/paper/1611.08307/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2016.

## Built on by (most cited first, 12 of 12)

- [Language-Agnostic Representation Learning of Source Code from Structure and Context](https://mlsanity.com/paper/2103.11318/) (2021)
- [Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs](https://mlsanity.com/paper/2103.09499/) (2021)
- [The Larger They Are, the Harder They Fail: Language Models do not Recognize Identifier Swaps in Python](https://mlsanity.com/paper/2305.15507/) (2023)
- [What to Retrieve for Effective Retrieval-Augmented Code Generation? An Empirical Study and Beyond](https://mlsanity.com/paper/2503.20589/) (2025)
- [AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://mlsanity.com/paper/2601.19697/) (2026)
- [A Survey of Deep Learning Models for Structural Code Understanding](https://mlsanity.com/paper/2205.01293/) (2022)
- [Senatus -- A Fast and Accurate Code-to-Code Recommendation Engine](https://mlsanity.com/paper/2111.04473/) (2021)
- [NeuDep: Neural Binary Memory Dependence Analysis](https://mlsanity.com/paper/2210.02853/) (2022)
- [Neural Machine Translation for Code Generation](https://mlsanity.com/paper/2305.13504/) (2023)
- [Deduplicating and Ranking Solution Programs for Suggesting Reference Solutions](https://mlsanity.com/paper/2307.07940/) (2023)
- [Borrowing from Similar Code: A Deep Learning NLP-Based Approach for Log Statement Automation](https://mlsanity.com/paper/2112.01259/) (2021)
- [Code Sophistication: From Code Recommendation to Logic Recommendation](https://mlsanity.com/paper/2201.07674/) (2022)

## Abstract (arXiv)

To enhance developer productivity, all modern integrated development environments (IDEs) include code suggestion functionality that proposes likely next tokens at the cursor. While current IDEs work well for statically-typed languages, their reliance on type annotations means that they do not provide the same level of support for dynamic programming languages as for statically-typed languages. Moreover, suggestion engines in modern IDEs do not propose expressions or multi-statement idiomatic code. Recent work has shown that language models can improve code suggestion systems by learning from software repositories. This paper introduces a neural language model with a sparse pointer network aimed at capturing very long-range dependencies. We release a large-scale code suggestion corpus of 41M lines of Python code crawled from GitHub. On this corpus, we found standard neural language models to perform well at suggesting local phenomena, but struggle to refer to identifiers that are introduced many tokens in the past. By augmenting a neural language model with a pointer network specialized in referring to predefined classes of identifiers, we obtain a much lower perplexity and a 5 percentage points increase in accuracy for code suggestion compared to an LSTM baseline. In fact, this increase in code suggestion accuracy is due to a 13 times more accurate prediction of identifiers. Furthermore, a qualitative analysis shows this model indeed captures interesting long-range dependencies, like referring to a class member defined over 60 tokens in the past.