基於文本豐富圖知識庫的結構與文本混合檢索

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

文本豐富的圖知識庫（TG-KBs）在回答查詢時提供文本和結構知識方面變得日益重要。然而，當前的檢索方法往往孤立地檢索這兩類知識，未考慮它們之間的相互強化，甚至有些混合方法在鄰域聚合後完全繞過結構檢索。為填補這一空白，我們提出了一種結構與文本混合檢索方法（MoR），通過規劃-推理-組織框架來檢索這兩類知識。在規劃階段，MoR生成描述回答查詢邏輯的文本規劃圖。依據規劃圖，在推理階段，MoR交織結構遍歷與文本匹配，從TG-KBs中獲取候選項。在組織階段，MoR進一步根據候選項的結構軌跡對其進行重新排序。大量實驗證明了MoR在協調結構與文本檢索方面的優越性，並揭示了不同查詢邏輯下檢索性能的不均衡性以及整合結構軌跡對候選項重新排序的益處。我們的代碼可在https://github.com/Yoega/MoR獲取。

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.