一句话：提出按自然语言查询为 API 类生成文档句子与方法组成的混合摘要。
在自动代码摘要领域，面向具体任务生成摘要仍具挑战。本文提出一种按需生成 API 类摘要的方法：给定以自然语言查询形式表达的编程任务，为相关 API 类生成“外延式”混合摘要。该摘要由两部分组成：从 API 参考文档中抽取的最相关句子，以及与任务最相关的方法。其目标不是概括类的全部行为，而是围绕查询提供能帮助开发者快速理解并完成特定编程任务的精炼信息。摘要同时结合文本与代码元素，因此称为混合摘要。摘要未报告具体评估结果。
Source code summaries are concise representations, in form of text and/or code, of complex code elements and are meant to help developers gain a quick understanding that in turns help them perform specific tasks. Generation of summaries that are task-specific is still a challenge in the automatic code summarization field. We propose an approach for generating on-demand, extrinsic hybrid summaries for API classes, relevant to a programming task, formulated as a natural language query. The summaries include the most relevant sentences extracted from the API reference documentation and the most relevant methods.
DOI 原文 ·
@inproceedings{paperbot5142,
title = {Generating query-specific class API summaries},
author = {Mingwei Liu and Xin Peng and Andrian Marcus and Zhenchang Xing and Wenkai Xie and Shuangshuang Xing and Yang Liu},
booktitle = {FSE},
year = {2019},
doi = {10.1145/3338906.3338971}
}