A Neural Question Answering System for Basic Questions about Subroutines
A Neural Question Answering System for Basic Questions about Subroutines
复制标题
DOI：
10.1109/saner50967.2021.00015
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Aakash Bansal;Zachary Eberhart;Lingfei Wu;Collin McMillan
中科院分区：
文献类型：
--
作者：
Aakash Bansal;Zachary Eberhart;Lingfei Wu;Collin McMillan
问答 (QA) 系统是一种对话式人工智能，可以为人类用户提出的问题生成自然语言答案。 QA 系统通常构成交互式对话系统的支柱，并且已针对从餐厅推荐到医疗诊断等各种任务进行了广泛的研究。近年来取得了巨大的进步，特别是使用经过大数据输入训练的编码器-解码器神经架构。在本文中，我们采取初步措施，通过针对子例程的基本问题设计基于上下文的 QA 系统，将最先进的神经 QA 技术引入软件工程应用。我们根据从最近的实证研究中提取的规则，整理了包含 1090 万个问题/上下文/答案元组的训练数据集。然后，我们使用该数据集训练自定义神经 QA 模型，并在与专业程序员的研究中评估该模型。我们展示了该系统的优点和缺点，并为其在软件工程的最终对话系统中的使用奠定了基础。
A question answering (QA) system is a type of conversational AI that generates natural language answers to questions posed by human users. QA systems often form the backbone of interactive dialogue systems, and have been studied extensively for a wide variety of tasks ranging from restaurant recommendations to medical diagnostics. Dramatic progress has been made in recent years, especially from the use of encoder-decoder neural architectures trained with big data input. In this paper, we take initial steps to bringing state-of-the-art neural QA technologies to Software Engineering applications by designing a context-based QA system for basic questions about subroutines. We curate a training dataset of 10.9 million question/context/answer tuples based on rules we extract from recent empirical studies. Then, we train a custom neural QA model with this dataset and evaluate the model in a study with professional programmers. We demonstrate the strengths and weaknesses of the system, and lay the groundwork for its use in eventual dialogue systems for software engineering.