Editable AI: Mixed Human-AI Authoring of Code Patterns
Editable AI: Mixed Human-AI Authoring of Code Patterns
复制标题
DOI：
10.1109/vlhcc.2019.8818871
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Kartik Chugh;Andrea Y. Solis;Thomas D. Latoza
中科院分区：
文献类型：
--
作者：
Kartik Chugh;Andrea Y. Solis;Thomas D. Latoza
编写HTML文档的开发人员根据模式定义元素，这些模式建立并反映了文档的视觉结构，例如通过对每个图像应用一个类来使页脚中的所有图像具有相同的高度。为了向开发人员展示这些模式，并支持开发人员根据这些模式进行创作，我们提出了一种用于创建代码模式的混合人工智能技术。模式首先通过决策树从单个HTML文档中学习，生成开发人员可以查看和编辑的表示。代码模式用于为开发人员提供自动完成建议、列表示例和标记违规。为了评估我们的技术，我们进行了一项用户研究，其中有24名参与者编写、编辑和更正HTML文档。我们发现，我们的技术使开发人员能够更快地编辑和更正文档，并更成功地创建，编辑和更正文档。
Developers authoring HTML documents define elements following patterns which establish and reflect the visual structure of a document, such as making all images in a footer the same height by applying a class to each. To surface these patterns to developers and support developers in authoring consistent with these patterns, we propose a mixed human-AI technique for creating code patterns. Patterns are first learned from individual HTML documents through a decision tree, generating a representation which developers may view and edit. Code patterns are used to offer developers autocomplete suggestions, list examples, and flag violations. To evaluate our technique, we conducted a user study in which 24 participants wrote, edited, and corrected HTML documents. We found that our technique enabled developers to edit and correct documents more quickly and create, edit, and correct documents more successfully.