# Toward Human-Like Summaries Generated from Heterogeneous Software Artefacts

## TL;DR

This paper explores methods to automatically generate human-like multi-document summaries from diverse software artefacts, aiming to improve software development efficiency and quality.

## Contribution

It introduces an initial approach analyzing human-written summaries to inform heuristics for automatic, human-like summarization of heterogeneous software artefacts.

## Key findings

- Analysis of 545 human summaries from 15 projects
- Identification of text properties guiding summary generation
- Foundation for heuristic-based automatic summarization

## Abstract

Automatic text summarisation has drawn considerable interest in the field of software engineering. It can improve the efficiency of software developers, enhance the quality of products, and ensure timely delivery. In this paper, we present our initial work towards automatically generating human-like multi-document summaries from heterogeneous software artefacts. Our analysis of the text properties of 545 human-written summaries from 15 software engineering projects will ultimately guide heuristics searches in the automatic generation of human-like summaries.