机器能学会使用搜索引擎作为寻找信息的互动工具吗？这将对使世界上的知识更容易获得产生深远的影响。本文介绍了在设计学习元策略的代理方面的第一步，这些元策略用于上下文查询的细化。我们的方法使用机器阅读来指导从聚合的搜索结果中选择精炼术语。然后，代理被赋予简单而有效的搜索操作符，以对查询和搜索结果进行细粒度和透明的控制。我们开发了一种生成合成搜索会话的新方法，它通过（自我）监督学习，利用了基于转化器的生成性语言模型的力量。我们还提出了一个具有动态约束行动的强化学习代理，可以完全从头开始学习交互式搜索策略。在这两种情况下，我们都获得了比具有强大信息检索基线的一次性搜索更明显的改进。最后，我们对所学的搜索策略进行了深入分析。
原文题目：Boosting Search Engines with Interactive Agents
原文：Can machines learn to use a search engine as an interactive tool for finding information? That would have far reaching consequences for making the world's knowledge more accessible. This paper presents first steps in designing agents that learn meta-strategies for contextual query refinements. Our approach uses machine reading to guide the selection of refinement terms from aggregated search results. Agents are then empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results. We develop a novel way of generating synthetic search sessions, which leverages the power of transformer-based generative language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that can learn interactive search strategies completely from scratch. In both cases, we obtain significant improvements over one-shot search with a strong information retrieval baseline. Finally, we provide an in-depth analysis of the learned search policies.
用交互式代理促进搜索引擎的发展.pdf