论文标题
Conco：会话编程需要什么？机器学习界面设计的探索
Convo: What does conversational programming need? An exploration of machine learning interface design
论文作者
论文摘要
自然语言理解和语音识别的大幅改善为与计算机的对话互动铺平了道路。尽管对话代理通常用于简短的面向目标对话框，但我们对开发计算机程序的代理知之甚少。为了探索自然语言用于编程的实用性，我们进行了一项研究（$ n $ = 45），将不同的输入方法与我们开发的对话编程系统进行了比较。参与者使用基于语音的，基于文本和语音或文本的系统完成了新手和高级任务。我们发现，用户赞赏每个系统的方面（例如，语音输入效率，文本输入精度），而新手用户对使用语音输入的编程更乐观，而不是高级用户。我们的结果表明，未来的对话编程工具应针对用户的编程经验量身定制，并允许用户选择其首选输入模式。为了减少认知负载，未来的接口可以结合可视化，并具有自然的自然语言理解和语音识别模型用于编程。
Vast improvements in natural language understanding and speech recognition have paved the way for conversational interaction with computers. While conversational agents have often been used for short goal-oriented dialog, we know little about agents for developing computer programs. To explore the utility of natural language for programming, we conducted a study ($n$=45) comparing different input methods to a conversational programming system we developed. Participants completed novice and advanced tasks using voice-based, text-based, and voice-or-text-based systems. We found that users appreciated aspects of each system (e.g., voice-input efficiency, text-input precision) and that novice users were more optimistic about programming using voice-input than advanced users. Our results show that future conversational programming tools should be tailored to users' programming experience and allow users to choose their preferred input mode. To reduce cognitive load, future interfaces can incorporate visualizations and possess custom natural language understanding and speech recognition models for programming.
