Re-finding information is an essential activity, however, it can be difficult when people struggle to express what they are looking for. Through a need-finding survey, we first seek opportunities for improving re-finding experiences, and explore one of these opportunities by implementing the FoundWright system. The system leverages recent advances in language transformer models to expand people's ability to express what they are looking for, through the interactive creation and manipulation of concepts contained within documents. We use FoundWright as a design probe to understand (1) how people create and use concepts, (2) how this expanded ability helps re-finding, and (3) how people engage and collaborate with FoundWright's machine learning support. Our probe reveals that this expanded way of expressing re-finding goals helps people with the task, by complementing traditional searching and browsing. Finally, we present insights and recommendations for future work aiming at developing systems to support re-finding.

翻译：重新查找信息是一项基本活动，然而当人们难以表达其搜索目标时，这一过程可能变得困难。通过一项需求发现调查，我们首先探索改进重新查找体验的机会，并通过实现FoundWright系统来研究其中一种机会。该系统利用语言Transformer模型的最新进展，通过交互式创建和操作文档中包含的概念，扩展了用户表达搜索目标的能力。我们以FoundWright作为设计探针，以理解：（1）用户如何创建和使用概念；（2）这种扩展的表达能力如何帮助重新查找；（3）用户如何参与并与FoundWright的机器学习支持协作。我们的探针研究表明，这种扩展的重新查找目标表达方式通过补充传统的搜索与浏览方式，有效帮助用户完成任务。最后，我们为未来旨在开发支持重新查找的系统工作提供见解与建议。