用检索代替生成查询变体，显著提升问答性能预测效果
Revisiting Query Variants: The Advantage of Retrieval Over Generation of Query Variants for Effective QPP
- 从训练集直接检索相似查询变体，避免生成带来的主题漂移
- 通过相关文档扩展检索，实现两跳查询变体召回率提升
- 在TREC DL数据集上相比现有方法提升近20%，适用于神经排序模型
利用查询变体（QVs）——即与目标查询具有潜在相似信息需求的查询——已被证明能提升查询性能预测（QPP）的效果。现有基于QV的QPP方法通过查询扩展或非上下文嵌入生成QVs，可能引入主题漂移和幻觉。本文提出一种新方法：针对给定目标查询，从训练集（如MS MARCO）中检索QVs。为提高召回率，我们通过其标注的相关文档进行二次检索，获得两跳查询变体（2-hop QVs）。在TREC DL'19和DL'20上的实验表明，采用本方法检索的QVs使QPP方法在如MonoT5等神经排序模型上的表现优于现有最佳生成式方法约20%。
原文摘要 · Abstract (English)
Leveraging query variants (QVs), i.e., queries with potentially similar information needs to the target query, has been shown to improve the effectiveness of query performance prediction (QPP) approaches. Existing QV-based QPP methods generate QVs facilitated by either query expansion or non-contextual embeddings, which may introduce topical drifts and hallucinations. In this paper, we propose a method that retrieves QVs from a training set (e.g., MS MARCO) for a given target query of QPP. To achieve a high recall in retrieving queries with the most similar information needs as the target query from a training set, we extend the directly retrieved QVs (1-hop QVs) by a second retrieval using their denoted relevant documents (which yields 2-hop QVs). Our experiments, conducted on TREC DL'19 and DL'20, show that the QPP methods with QVs retrieved by our method outperform the best-performing existing generated-QV-based QPP approaches by as much as around 20\%, on neural ranking models like MonoT5.
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。