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

TL;DR

This paper introduces MoR, a novel framework that effectively combines structural and textual retrieval methods for text-rich graph knowledge bases, improving query answering accuracy.

Contribution

MoR is the first to integrate planning, reasoning, and organizing stages for joint structural and textual retrieval in TG-KBs.

Findings

MoR outperforms existing methods in retrieval tasks.

Structural trajectories enhance candidate reranking.

Performance varies with different query logics.

Abstract

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.