Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908389114642432 |
|---|---|
| author | Lei, Yongjia Han, Haoyu Rossi, Ryan A. Dernoncourt, Franck Lipka, Nedim Halappanavar, Mahantesh M Tang, Jiliang Wang, Yu |
| author_facet | Lei, Yongjia Han, Haoyu Rossi, Ryan A. Dernoncourt, Franck Lipka, Nedim Halappanavar, Mahantesh M Tang, Jiliang Wang, Yu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20317 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases Lei, Yongjia Han, Haoyu Rossi, Ryan A. Dernoncourt, Franck Lipka, Nedim Halappanavar, Mahantesh M Tang, Jiliang Wang, Yu Machine Learning Artificial Intelligence Information Retrieval 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. |
| title | Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Bases |
| topic | Machine Learning Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2502.20317 |