会话搜索风险的模拟与建模
Simulating and Modeling the Risk of Conversational Search
摘要：
在对话式搜索中，代理可以通过询问澄清问题来与用户交互，以增加他们找到更好结果的机会。NLP和IR社区最近的许多工作和共同任务都集中在确定提出澄清问题的需要和产生问题的方法上。这些工作假设问澄清问题是一个安全的替代检索结果。由于现有的会话搜索模型远非完美，它们可能会检索或生成不好的澄清问题。当用户更喜欢搜索效率而不是正确性时，问太多澄清性问题也会耗尽用户的耐心。因此，这些模型可能会适得其反，并损害用户的搜索体验，因为这些风险通过提出澄清问题。在这项工作中，我们提出了一个模拟框架来模拟在会话搜索中提出问题的风险，并进一步修改了一个风险感知的会话搜索模型来控制风险。我们通过对三个会话数据集的广泛实验来展示该模型的鲁棒性和有效性，包括MSDialog，Ubuntu Dialog语料库和Opendialkg，并将其与多个基线进行比较。我们表明，风险控制模块可以与两种不同的重新排序模型，并在我们的大多数实验中优于所有的基线。
英文摘要：
In conversational search, agents can interact with users by asking clarifying questions to increase their chance to find better results. Many recent works and shared tasks in both NLP and IR communities have focused on identifying the need of asking clarifying questions and methodologies of generating them. These works assume asking clarifying questions is a safe alternative to retrieving results. As existing conversational search models are far from perfect, it's possible and common that they could retrieve or generate bad clarifying questions. Asking too many clarifying questions can also drain user's patience when the user prefers searching efficiency over correctness. Hence, these models can get backfired and harm user's search experience because of these risks by asking clarifying questions. In this work, we propose a simulation framework to simulate the risk of asking questions in conversational search and further revise a risk-aware conversational search model to control the risk. We show the model's robustness and effectiveness through extensive experiments on three conversations datasets, including MSDialog, Ubuntu Dialog Corpus, and Opendialkg in which we compare it with multiple baselines. We show that the risk-control module can work with two different re-ranker models and outperform all the baselines in most of our experiments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
