ComSum: Commit Messages Summarization and Meaning Preservation

Leshem Choshen; Idan Amit

ComSum: Commit Messages Summarization and Meaning Preservation

Computation and Language 2021-08-25 v1 Machine Learning Software Engineering

Authors: Leshem Choshen , Idan Amit

Abstract

We present ComSum, a data set of 7 million commit messages for text summarization. When documenting commits, software code changes, both a message and its summary are posted. We gather and filter those to curate developers' work summarization data set. Along with its growing size, practicality and challenging language domain, the data set benefits from the living field of empirical software engineering. As commits follow a typology, we propose to not only evaluate outputs by Rouge, but by their meaning preservation.

Keywords

text summarization

Cite

@article{arxiv.2108.10763,
  title  = {ComSum: Commit Messages Summarization and Meaning Preservation},
  author = {Leshem Choshen and Idan Amit},
  journal= {arXiv preprint arXiv:2108.10763},
  year   = {2021}
}

Related papers

View all related →

Computation and Language · Computer Science

CommitBERT: Commit Message Generation Using Pre-Trained Programming Language Model