用蕴含关系优化文档检索，提升问答系统效果
Improve Dense Passage Retrieval with Entailment Tuning
- 将检索数据与自然语言推理任务统一为存在性断言形式
- 通过掩码预测任务训练模型识别文本蕴含关系，提升检索性能
- 可无缝接入现有检索框架，适合改进问答与生成系统
检索模块可嵌入多种下游NLP任务以提升性能，如开放域问答和检索增强生成。检索系统的核心在于计算查询与文档之间的相关性得分，但相关性的定义常不明确。我们观察到，多数相关性判断与自然语言推理（NLI）中的蕴含概念一致。基于此，我们提出蕴含微调（entailment tuning）方法，用于优化密集检索器的嵌入表示。具体而言，我们使用存在性断言作为桥梁，统一检索数据与NLI数据的形式，并设计一种变体掩码预测任务，让检索器预测文档中蕴含的断言。该方法可高效集成至现有密集检索方法中，实验表明其有效性。
原文摘要 · Abstract (English)
Retrieval module can be plugged into many downstream NLP tasks to improve their performance, such as open-domain question answering and retrieval-augmented generation. The key to a retrieval system is to calculate relevance scores to query and passage pairs. However, the definition of relevance is often ambiguous. We observed that a major class of relevance aligns with the concept of entailment in NLI tasks. Based on this observation, we designed a method called entailment tuning to improve the embedding of dense retrievers. Specifically, we unify the form of retrieval data and NLI data using existence claim as a bridge. Then, we train retrievers to predict the claims entailed in a passage with a variant task of masked prediction. Our method can be efficiently plugged into current dense retrieval methods, and experiments show the effectiveness of our method.
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。