Automatic text summarization systems commonly involve humans for preparing data or evaluating model performance, yet, there lacks a systematic understanding of humans' roles, experience, and needs when interacting with or being assisted by AI. From a human-centered perspective, we map the design opportunities and considerations for human-AI interaction in text summarization and broader text generation tasks. We first conducted a systematic literature review of 70 papers, developing a taxonomy of five interactions in AI-assisted text generation and relevant design dimensions. We designed text summarization prototypes for each interaction. We then interviewed 16 users, aided by the prototypes, to understand their expectations, experience, and needs regarding efficiency, control, and trust with AI in text summarization and propose design considerations accordingly.
翻译:自动文本汇总系统通常涉及编制数据或评价模型性能的人,然而,在与AI互动或得到其协助时,缺乏对人的作用、经验和需要的系统理解。从以人为中心的角度,我们绘制了在文本汇总和更广泛的文本生成任务方面人类与AI互动的设计机会和考虑。我们首先对70份文件进行了系统文献审查,对AI协助的文本生成和相关设计层面的5个互动进行了分类。我们为每次互动设计了文本汇总原型。我们随后在原型的帮助下与16个用户进行了访谈,以了解其在效率、控制和信任方面的期望、经验和需要,并据此提出设计考虑。