Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Muzhi, Yang, Cehao, Xu, Chengjin, Jiang, Xuhui, Qi, Yiyan, Guo, Jian, Leung, Ho-fung, King, Irwin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908343500537856
author Li, Muzhi
Yang, Cehao
Xu, Chengjin
Jiang, Xuhui
Qi, Yiyan
Guo, Jian
Leung, Ho-fung
King, Irwin
author_facet Li, Muzhi
Yang, Cehao
Xu, Chengjin
Jiang, Xuhui
Qi, Yiyan
Guo, Jian
Leung, Ho-fung
King, Irwin
contents The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle with the semantic gap between KG triples and natural language. Apart from triples, entity contexts (e.g., labels, descriptions, aliases) also play a significant role in augmenting KGs. To address these limitations, we propose KGR3, a context-enriched framework for KGC. KGR3 is composed of three modules. Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity. Then, the Reasoning module employs a large language model to generate potential answers for each query triple. Finally, the Re-ranking module combines candidate answers from the two modules mentioned above, and fine-tunes an LLM to provide the best answer. Extensive experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods. Specifically, the best variant of KGR3 achieves absolute Hits@1 improvements of 12.3% and 5.6% on the FB15k237 and WN18RR datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2411_08165
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
Li, Muzhi
Yang, Cehao
Xu, Chengjin
Jiang, Xuhui
Qi, Yiyan
Guo, Jian
Leung, Ho-fung
King, Irwin
Artificial Intelligence
Computation and Language
The Knowledge Graph Completion~(KGC) task aims to infer the missing entity from an incomplete triple. Existing embedding-based methods rely solely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. On the other hand, text-based methods struggle with the semantic gap between KG triples and natural language. Apart from triples, entity contexts (e.g., labels, descriptions, aliases) also play a significant role in augmenting KGs. To address these limitations, we propose KGR3, a context-enriched framework for KGC. KGR3 is composed of three modules. Firstly, the Retrieval module gathers supporting triples from the KG, collects plausible candidate answers from a base embedding model, and retrieves context for each related entity. Then, the Reasoning module employs a large language model to generate potential answers for each query triple. Finally, the Re-ranking module combines candidate answers from the two modules mentioned above, and fine-tunes an LLM to provide the best answer. Extensive experiments on widely used datasets demonstrate that KGR3 consistently improves various KGC methods. Specifically, the best variant of KGR3 achieves absolute Hits@1 improvements of 12.3% and 5.6% on the FB15k237 and WN18RR datasets.
title Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2411.08165