用语言学推理优化检索，让文档表示更区分性强
Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval
- 引入理性言语行为框架，动态调节词与文档的互动
- 在BEIR跨域数据集上超越现有稀疏检索模型
- 适合需要精准文档区分的检索场景
当前稀疏神经信息检索方法，以及传统的如BM25等模型，未能充分考虑文档集合中不同词权重间的复杂交互关系。本文将理性言语行为（Rational Speech Acts, RSA）框架——一种用于最小化识别集合中目标对象所需传递特征数量的语言学模型——适配到信息检索任务中，尤其针对高维特征空间（此处为词元）。该方法通过考虑数据集中其他文档的影响，动态调节词-文档之间的交互，从而增强文档表征的区分性。实验表明，引入RSA能持续提升多个稀疏检索模型的表现，并在BEIR基准的跨域数据集上达到当前最优性能。
原文摘要 · Abstract (English)
Current sparse neural information retrieval (IR) methods, and to a lesser extent more traditional models such as BM25, do not take into account the document collection and the complex interplay between different term weights when representing a single document. In this paper, we show how the Rational Speech Acts (RSA), a linguistics framework used to minimize the number of features to be communicated when identifying an object in a set, can be adapted to the IR case -- and in particular to the high number of potential features (here, tokens). RSA dynamically modulates token-document interactions by considering the influence of other documents in the dataset, better contrasting document representations. Experiments show that incorporating RSA consistently improves multiple sparse retrieval models and achieves state-of-the-art performance on out-of-domain datasets from the BEIR benchmark. https://github.com/arthur-75/Rational-Retrieval-Acts
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。