Year: 2022
Type: conference-paper
Abstract: Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits. To address this, we propose a novel pretraining objective which explicitly models edits and use it to build CoditT5, a large language model for software-related editing tasks that is pretrained on large amounts of source code and natural language comments. We fine-tune it on various downstream editing tasks, including comment updating, bug fixing, and automated code review. By outperforming standard generation-based models, we demonstrate the generalizability of our approach and its suitability for editing tasks. We also show how a standard generation model and our edit-based model can complement one another through simple reranking strategies, with which we achieve state-of-the-art performance for the three downstream editing tasks.
Institution: The University of Texas at Austin
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
Awards: Collaborative Research: SHF: Medium: Efficient and Trustworthy Proof Engineering, CAREER: Discourse Processing and Content Generation for Document Simplification, CAREER: Advancing Regression Testing: Theory and Practice, Collaborative Research: HCC: Medium: Fine-grained Emotion Analysis in Crises
OpenAlex ID: W4313547604
