用历史相关反馈重写查询，提升检索效果
Counterfactual Query Rewriting to Use Historical Relevance Feedback
- 基于过往相关文档内容重写查询词
- 在CLEF LongEval中优于传统方法，超越复杂Transformer模型
- 适合需要利用历史数据的在线检索系统
当检索系统遇到曾处理过的查询时，以往的相关性反馈（如点击或显式评分）可提升结果质量。然而，过去相关的文档内容可能已改变或不再可用。本文提出一种反事实策略：仍以这些历史相关文档作为相关性信号。通过从过往相关文档中提取关键词扩展查询，或生成能将旧相关文档排至前列的“关键查询”，来重写用户查询。在 CLEF LongEval 场景下的评估表明，使用历史反馈重写查询显著提升了检索效果，甚至优于计算开销较大的 Transformer 模型。
原文摘要 · Abstract (English)
When a retrieval system receives a query it has encountered before, previous relevance feedback, such as clicks or explicit judgments can help to improve retrieval results. However, the content of a previously relevant document may have changed, or the document might not be available anymore. Despite this evolved corpus, we counterfactually use these previously relevant documents as relevance signals. In this paper we proposed approaches to rewrite user queries and compare them against a system that directly uses the previous qrels for the ranking. We expand queries with terms extracted from the previously relevant documents or derive so-called keyqueries that rank the previously relevant documents to the top of the current corpus. Our evaluation in the CLEF LongEval scenario shows that rewriting queries with historical relevance feedback improves the retrieval effectiveness and even outperforms computationally expensive transformer-based approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。