A Wizard of Oz Study Simulating API Usage Dialogues With a Virtual Assistant
A Wizard of Oz Study Simulating API Usage Dialogues With a Virtual Assistant
复制标题
DOI：
10.1109/tse.2020.3040935
复制
发表时间：
2021-06
影响因子：
7.4
通讯作者：
Zachary Eberhart;Aakash Bansal;Collin McMillan
中科院分区：
文献类型：
--
作者：
Zachary Eberhart;Aakash Bansal;Collin McMillan
虚拟助手技术正在迅速普及，以提高各种任务的生产力。虽然用于日常任务的几个虚拟助理是众所周知的（例如，Siri，Cortana，Alexa），软件工程等专业任务的助理则更少。软件工程助理很少的一个关键原因是，很少有实验数据集可用于训练人工智能，而人工智能是当前虚拟助理的基础。在本文中，我们提出了一组绿野仙踪实验，我们设计来构建一个数据集，用于创建一个虚拟助手。我们的目标是一个虚拟助手，帮助程序员使用API。在我们的实验中，我们招募了30名专业程序员，使用两个API完成编程任务。程序员与一个模拟的虚拟助手进行交互以寻求帮助-程序员并不知道助手实际上是由人类专家操作的。然后，我们在语料库中注释的对话行为沿着四个维度：言外之意，API信息类型（S），面向后的功能，并可追溯到特定的API组件。我们观察到了各种各样的交互，这将有助于虚拟助手为API使用开发对话策略。
Virtual Assistant technology is rapidly proliferating to improve productivity in a variety of tasks. While several virtual assistants for everyday tasks are well-known (e.g., Siri, Cortana, Alexa), assistants for specialty tasks such as software engineering are rarer. One key reason software engineering assistants are rare is that very few experimental datasets are available and suitable for training the AI that is the bedrock of current virtual assistants. In this paper, we present a set of Wizard of Oz experiments that we designed to build a dataset for creating a virtual assistant. Our target is a hypothetical virtual assistant for helping programmers use APIs. In our experiments, we recruited 30 professional programmers to complete programming tasks using two APIs. The programmers interacted with a simulated virtual assistant for help – the programmers were not aware that the assistant was actually operated by human experts. We then annotated the dialogue acts in the corpus along four dimensions: illocutionary intent, API information type(s), backward-facing function, and traceability to specific API components. We observed a diverse range of interactions that will facilitate the development of dialogue strategies for virtual assistants for API usage.