Toward Human-Like Summaries Generated from Heterogeneous Software\n Artefacts

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