# Learning to Represent Edits

arXiv: https://arxiv.org/abs/1810.13337 · HTML: https://mlsanity.com/paper/1810.13337/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2018.

## Built on by (most cited first, 30 of 34)

- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [CoditT5: Pretraining for Source Code and Natural Language Editing](https://mlsanity.com/paper/2208.05446/) (2022)
- [DiffusER: Discrete Diffusion via Edit-based Reconstruction](https://mlsanity.com/paper/2210.16886/) (2022)
- [Neural Transfer Learning for Repairing Security Vulnerabilities in C Code](https://mlsanity.com/paper/2104.08308/) (2021)
- [Learning to Model Editing Processes](https://mlsanity.com/paper/2205.12374/) (2022)
- [InstructCoder: Instruction Tuning Large Language Models for Code Editing](https://mlsanity.com/paper/2310.20329/) (2023)
- [Beyond In-Place Corruption: Insertion and Deletion In Denoising Probabilistic Models](https://mlsanity.com/paper/2107.07675/) (2021)
- [InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2302.08624/) (2023)
- [VELVET: a noVel Ensemble Learning approach to automatically locate VulnErable sTatements](https://mlsanity.com/paper/2112.10893/) (2021)
- [NewsEdits: A News Article Revision Dataset and a Document-Level Reasoning Challenge](https://mlsanity.com/paper/2206.07106/) (2022)
- [Learning Structural Edits via Incremental Tree Transformations](https://mlsanity.com/paper/2101.12087/) (2021)
- [GrACE: Generation using Associated Code Edits](https://mlsanity.com/paper/2305.14129/) (2023)
- [On Distribution Shift in Learning-based Bug Detectors](https://mlsanity.com/paper/2204.10049/) (2022)
- [KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair](https://mlsanity.com/paper/2302.01857/) (2023)
- [Context-NER : Contextual Phrase Generation at Scale](https://mlsanity.com/paper/2109.08079/) (2021)
- [VarCLR: Variable Semantic Representation Pre-training via Contrastive Learning](https://mlsanity.com/paper/2112.02650/) (2021)
- [Fix Bugs with Transformer through a Neural-Symbolic Edit Grammar](https://mlsanity.com/paper/2204.06643/) (2022)
- [Overwatch: Learning Patterns in Code Edit Sequences](https://mlsanity.com/paper/2207.12456/) (2022)
- [Controlling Text Edition by Changing Answers of Specific Questions](https://mlsanity.com/paper/2105.11018/) (2021)
- [XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates](https://mlsanity.com/paper/2309.11063/) (2023)
- [Unsupervised Learning of General-Purpose Embeddings for Code Changes](https://mlsanity.com/paper/2106.02087/) (2021)
- [CCRep: Learning Code Change Representations via Pre-Trained Code Model and Query Back](https://mlsanity.com/paper/2302.03924/) (2023)
- [EDM3: Event Detection as Multi-task Text Generation](https://mlsanity.com/paper/2305.16357/) (2023)
- [NewsEdits: A Dataset of Revision Histories for News Articles (Technical Report: Data Processing)](https://mlsanity.com/paper/2104.09647/) (2021)
- [Interactive Text Generation](https://mlsanity.com/paper/2303.00908/) (2023)
- [Assessing the Effectiveness of Syntactic Structure to Learn Code Edit Representations](https://mlsanity.com/paper/2106.06110/) (2021)
- [LAMNER: Code Comment Generation Using Character Language Model and Named Entity Recognition](https://mlsanity.com/paper/2204.09654/) (2022)
- [Implant Global and Local Hierarchy Information to Sequence based Code Representation Models](https://mlsanity.com/paper/2303.07826/) (2023)
- [Just-In-Time Software Defect Prediction via Bi-modal Change Representation Learning](https://mlsanity.com/paper/2410.12107/) (2024)
- [Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networks](https://mlsanity.com/paper/2506.18191/) (2025)

## Abstract (arXiv)

We introduce the problem of learning distributed representations of edits. By combining a "neural editor" with an "edit encoder", our models learn to represent the salient information of an edit and can be used to apply edits to new inputs. We experiment on natural language and source code edit data. Our evaluation yields promising results that suggest that our neural network models learn to capture the structure and semantics of edits. We hope that this interesting task and data source will inspire other researchers to work further on this problem.