一句话：提出基于学习的方法，从 API 文档中抽取 API 指令并转换为便于工具处理的一阶逻辑表示。
开发者常依赖 API 文档来了解 API 指令，即与 API 使用相关的约束和指南。不遵循这些指令可能导致缺陷或不正确的实现。由于业界缺乏统一的 API 指令文档规范，指令形式多样，开发者难以理解，工具也难以解析。该论文提出一种基于学习的方法，从 API 文档中自动抽取 API 指令，并将其表示为一阶逻辑公式，从而以结构化、可被工具处理的语义形式捕获这些约束和指南。摘要未报告具体的评估设置与实验结果；从标题和摘要看，工作的核心贡献在于将自然语言 API 文档中的指令转化为一阶逻辑表示，为后续的自动化检查、推理与开发者工具支持奠定基础。
Developers often rely on API documentation to learn API directives, i.e., constraints and guidelines related to API usage. Failing to follow API directives may cause defects or improper implementations. Since there are no industry-wide standards on how to document API directives, they take many forms and are often hard to understand by developers or challenging to parse with tools.
DOI 原文 ·
@inproceedings{paperbot6361,
title = {Learning-based extraction of first-order logic representations of API directives},
author = {Mingwei Liu and Xin Peng and Andrian Marcus and Christoph Treude and Xuefang Bai and Gang Lyu and Jiazhan Xie and Xiaoxin Zhang},
booktitle = {FSE},
year = {2021},
doi = {10.1145/3468264.3468618}
}