Editable AI: Mixed Human-AI Authoring of Code Patterns
This addresses the problem of improving code consistency and efficiency for web developers, though it is incremental as it builds on existing pattern-learning methods.
The paper tackled the problem of helping developers author consistent HTML patterns by proposing a mixed human-AI technique that learns patterns from documents and provides autocomplete suggestions and violation flags. In a user study with 24 participants, it enabled developers to edit and correct documents more quickly and successfully.
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.