Learning to Represent Edits

TL;DR

This paper presents a novel approach to learning distributed representations of edits in natural language and source code, enabling models to understand and apply edits effectively.

Contribution

It introduces the concept of neural editors combined with edit encoders to capture the structure and semantics of edits, a new task in representation learning.

Findings

Models learn to capture edit structure and semantics

Promising results in applying edits to new inputs

Encourages further research in edit representation learning

Abstract

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.