arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.07093cs.CL
收藏

基于上下文线索抽样和语言模型的查询扩展

Query Expansion Using Contextual Clue Sampling with Language Models

University College London(伦敦大学学院);University of Waterloo(滑铁卢大学)

Linqing Liu, Minghan Li, Jimmy Lin, Sebastian Riedel, Pontus Stenetorp

摘要:

查询扩展是信息检索中缓解查询词与文档词汇不匹配的有效方法。最近的一项研究使用语言模型来生成查询相关的上下文以供扩展。沿着这条线,我们认为,从这些背景下的扩展条款应该平衡两个关键方面:多样性和相关性。增加多样性的明显方法是从语言模型中抽取多个上下文。然而,这是以相关性为代价的,因为模型有一个众所周知的倾向,即产生不正确或不相关的上下文。为了平衡这两个方面的考虑,我们提出了一个有效的过滤策略和融合的基础上,每个上下文的生成概率检索到的文件相结合。我们的基于词汇匹配的方法实现了类似的前5名/前20名的检索准确率和更高的前100名的准确率相比,建立良好的稠密检索模型DPR,同时减少了超过96%的索引大小。对于端到端QA,读者模型也受益于我们的方法,并在几个竞争基线中获得了最高的精确匹配分数。

英文摘要:

Query expansion is an effective approach for mitigating vocabulary mismatch between queries and documents in information retrieval. One recent line of research uses language models to generate query-related contexts for expansion. Along this line, we argue that expansion terms from these contexts should balance two key aspects: diversity and relevance. The obvious way to increase diversity is to sample multiple contexts from the language model. However, this comes at the cost of relevance, because there is a well-known tendency of models to hallucinate incorrect or irrelevant contexts. To balance these two considerations, we propose a combination of an effective filtering strategy and fusion of the retrieved documents based on the generation probability of each context. Our lexical matching based approach achieves a similar top-5/top-20 retrieval accuracy and higher top-100 accuracy compared with the well-established dense retrieval model DPR, while reducing the index size by more than 96%. For end-to-end QA, the reader model also benefits from our method and achieves the highest Exact-Match score against several competitive baselines.

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。

↑