基于文本丰富图知识库的结构化与文本检索混合方法

Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases

February 27, 2025

作者: Yongjia Lei, Haoyu Han, Ryan A. Rossi, Franck Dernoncourt, Nedim Lipka, Mahantesh M Halappanavar, Jiliang Tang, Yu Wang

cs.AI

摘要

富含文本的图知识库（TG-KBs）在通过提供文本与结构知识来回答查询方面变得日益重要。然而，现有的检索方法往往孤立地获取这两种知识，未考虑它们之间的相互增强作用，甚至有些混合方法在邻近聚合后完全绕过了结构检索。为填补这一空白，我们提出了一种结构-文本混合检索方法（MoR），通过规划-推理-组织框架来检索这两种知识。在规划阶段，MoR生成文本规划图，勾勒出回答查询的逻辑路径。依据规划图，在推理阶段，MoR交织结构遍历与文本匹配，从TG-KBs中获取候选答案。在组织阶段，MoR进一步根据候选答案的结构轨迹进行重排序。大量实验证明了MoR在协调结构与文本检索方面的优越性，揭示了不同查询逻辑下检索性能的差异，以及整合结构轨迹对候选答案重排序的益处。我们的代码已发布于https://github.com/Yoega/MoR。

English

Text-rich Graph Knowledge Bases (TG-KBs) have become increasingly crucial for answering queries by providing textual and structural knowledge. However, current retrieval methods often retrieve these two types of knowledge in isolation without considering their mutual reinforcement and some hybrid methods even bypass structural retrieval entirely after neighboring aggregation. To fill in this gap, we propose a Mixture of Structural-and-Textual Retrieval (MoR) to retrieve these two types of knowledge via a Planning-Reasoning-Organizing framework. In the Planning stage, MoR generates textual planning graphs delineating the logic for answering queries. Following planning graphs, in the Reasoning stage, MoR interweaves structural traversal and textual matching to obtain candidates from TG-KBs. In the Organizing stage, MoR further reranks fetched candidates based on their structural trajectory. Extensive experiments demonstrate the superiority of MoR in harmonizing structural and textual retrieval with insights, including uneven retrieving performance across different query logics and the benefits of integrating structural trajectories for candidate reranking. Our code is available at https://github.com/Yoega/MoR.