A comparison of lightweight ML models for commit message generation finds a cosine-similarity TF-IDF retrieval model reaches BLEU 16.82, below RACE's 25.66, while ChatGPT was preferred in manual evaluation.
A Neural Architecture for Generating Natural Language Descriptions from Source Code Changes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We propose a model to automatically describe changes introduced in the source code of a program using natural language. Our method receives as input a set of code commits, which contains both the modifications and message introduced by an user. These two modalities are used to train an encoder-decoder architecture. We evaluated our approach on twelve real world open source projects from four different programming languages. Quantitative and qualitative results showed that the proposed approach can generate feasible and semantically sound descriptions not only in standard in-project settings, but also in a cross-project setting.
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Automated Generation of Commit Messages in Software Repositories
A comparison of lightweight ML models for commit message generation finds a cosine-similarity TF-IDF retrieval model reaches BLEU 16.82, below RACE's 25.66, while ChatGPT was preferred in manual evaluation.