Scholarlink

<p>Knowledge graphs (KGs) is an associated network composed of semantic relationships. The goal of the knowledge graph question answering (KGQA) is to provide answers to natural language questions based on KGs. Multi-hop KGQA requires reasoning on multiple edges of KGs to get the correct answer. However, KGs are usually incomplete, with numerous missing relationships in reality, which brings challenges to KGQA, especially for multi-hop KGQA. In this work, we propose an efficient approach for multi-hop KGQA. To capture more comprehensive features on incomplete KGs, we utilize Tucker Entity Relation (TuckER) decomposition for link prediction on the binary tensor representation of KGs and train a knowledge graph embedding (KGE) model and apply the learned representation for downstream QA tasks. We employ a pre-trained language model to assess the relevance scoring of questions and each node after subgraph retrieval. Additionally, we introduce a link scoring strategy based on the triple scoring function to address the limitations of solely relying on KGE for answer scoring. Through extensive experiments conducted on multiple benchmark datasets, we demonstrate the effectiveness of our proposed model in facilitating multi-hop QA reasoning on incomplete KGs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Subgraph retrieval and link scoring model for multi-hop question answering in knowledge graphs

  • 期刊论文

  • 发表日期：

    2025年2月10日

查看全文
  • Changshun Zhou,
  • Wenhao Ying,
  • Shan Zhong,
  • Shengrong Gong,
  • Han Yan

摘要

Knowledge graphs (KGs) is an associated network composed of semantic relationships. The goal of the knowledge graph question answering (KGQA) is to provide answers to natural language questions based on KGs. Multi-hop KGQA requires reasoning on multiple edges of KGs to get the correct answer. However, KGs are usually incomplete, with numerous missing relationships in reality, which brings challenges to KGQA, especially for multi-hop KGQA. In this work, we propose an efficient approach for multi-hop KGQA. To capture more comprehensive features on incomplete KGs, we utilize Tucker Entity Relation (TuckER) decomposition for link prediction on the binary tensor representation of KGs and train a knowledge graph embedding (KGE) model and apply the learned representation for downstream QA tasks. We employ a pre-trained language model to assess the relevance scoring of questions and each node after subgraph retrieval. Additionally, we introduce a link scoring strategy based on the triple scoring function to address the limitations of solely relying on KGE for answer scoring. Through extensive experiments conducted on multiple benchmark datasets, we demonstrate the effectiveness of our proposed model in facilitating multi-hop QA reasoning on incomplete KGs.