论文标题
INSCIT：与混合互动的信息寻求对话
INSCIT: Information-Seeking Conversations with Mixed-Initiative Interactions
论文作者
论文摘要
在寻求信息的对话中，用户可能会提出未指定或无法回答的问题。理想的代理人将根据可用的知识源启动不同的响应类型来进行交互。但是，大多数目前的研究都无法或人为地纳入了这种代理端倡议。这项工作介绍了INSCIT，这是一种用于通过混合互动的信息进行信息对话的数据集。它包含从805个人类对话中进行的4.7k用户代理转弯，代理商对Wikipedia进行搜索，然后直接答案，要求澄清或提供相关信息以解决用户查询。数据支持两个子任务，证据通过识别和响应产生，以及评估模型绩效的人类评估协议。我们根据对话知识识别和开放域问题的最新模型报告了两个系统的结果。这两种系统都显着不足，这表明未来的研究中有足够的改进空间。
In an information-seeking conversation, a user may ask questions that are under-specified or unanswerable. An ideal agent would interact by initiating different response types according to the available knowledge sources. However, most current studies either fail to or artificially incorporate such agent-side initiative. This work presents InSCIt, a dataset for Information-Seeking Conversations with mixed-initiative Interactions. It contains 4.7K user-agent turns from 805 human-human conversations where the agent searches over Wikipedia and either directly answers, asks for clarification, or provides relevant information to address user queries. The data supports two subtasks, evidence passage identification and response generation, as well as a human evaluation protocol to assess model performance. We report results of two systems based on state-of-the-art models of conversational knowledge identification and open-domain question answering. Both systems significantly underperform humans, suggesting ample room for improvement in future studies.
