一句话：提出 GUI2WiRe，用多种 IR 模型与自动查询扩展从大规模 GUI 仓库按自然语言需求检索原型并快速生成线框图。
高保真 GUI 原型有助于澄清与细化客户需求，但其制作耗时且昂贵。本文提出 GUI2WiRe 工具：从半自动构建的大规模移动应用 GUI 仓库中抽取 GUI 层级数据里的多段文本，结合多种信息检索模型与自动查询扩展技术，实现由自然语言需求到 GUI 原型的即席检索；检索到的原型可插入图形编辑器，系统自动抽取 GUI 组件并提供基本编辑功能，再由线框图生成可交互的应用预览。作者在人工标注的自然语言需求集合上评估了所采用的 IR 与 AQE 方法在 GUI 检索相关性上的效果，并讨论了计划中的用户研究。
High-fidelity Graphical User Interface (GUI) prototyping is a well-established and suitable method for enabling fruitful discussions, clarification and refinement of requirements formulated by customers. GUI prototypes can help to reduce misunderstandings between customers and developers, which may occur due to the ambiguity comprised in informal Natural Language (NL). However, a disadvantage of employing high-fidelity GUI prototypes is their time-consuming and expensive development. Common GUI prototyping tools are based on combining individual GUI components or manually crafted templates. In this work, we present GUI2WiRe, a tool that enables users to retrieve GUI prototypes from a semiautomatically created large-scale GUI repository for mobile applications matching user requirements specified in Natural Language (NLR). We extract multiple text segments from the GUI hierarchy data and employ various Information Retrieval (IR) models and Automatic Query Expansion (AQE) techniques to achieve ad-hoc GUI retrieval from NLR. Retrieved GUI prototypes mined from applications can be inserted in the graphical editor of GUI2WiRe to rapidly create wireframes. GUI components are extracted automatically from the GUI screenshots and basic editing functionality is provided to the user. Finally, a preview of the application is created from the wireframe to allow interactive exploration of the current design. We evaluated the applied IR and AQE approaches for their effectiveness in terms of GUI retrieval relevance on a manually annotated collection of NLR and discuss our planned user studies. Video presentation of GUI2WiRe: https://youtu.be/2nN-Xr2Hk7I
DOI 原文 ·
@inproceedings{paperbot5872,
title = {GUI2WiRe},
author = {Kristian Kolthoff and Christian Bartelt and Simone Paolo Ponzetto},
booktitle = {ASE},
year = {2020},
doi = {10.1145/3324884.3415289}
}