arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.04410cs.IR
收藏

基于强化学习的Web搜索查询评价优化

Optimizing Query Evaluations using Reinforcement Learning for Web Search

Corby Rosset, Damien Jose, Gargi Ghosh, Bhaskar Mitra, Saurabh Tiwary

摘要:

在网络搜索中,通常候选生成步骤从包含多达数十亿个网页的集合中选择一小组文档,这些文档随后在呈现给用户之前进行排名和修剪。在Bing中,候选生成涉及使用静态设计的匹配计划扫描索引,这些计划规定了不同匹配标准和停止条件的序列。在这项工作中,我们将匹配规划作为一个强化学习任务,并观察到访问的索引块减少了20%,候选集的质量下降很少或没有下降。

英文摘要:

In web search, typically a candidate generation step selects a small set of documents---from collections containing as many as billions of web pages---that are subsequently ranked and pruned before being presented to the user. In Bing, the candidate generation involves scanning the index using statically designed match plans that prescribe sequences of different match criteria and stopping conditions. In this work, we pose match planning as a reinforcement learning task and observe up to 20% reduction in index blocks accessed, with small or no degradation in the quality of the candidate sets.

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。

↑