Hierarchy-Aware Multi-Hop Question Answering over Knowledge Graphs
Open Access
- 30 April 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2519-2527
Abstract
Knowledge graphs (KGs) have been widely used to enhance complex question answering (QA). To understand complex questions, existing studies employ language models (LMs) to encode contexts. Despite the simplicity, they neglect the latent relational information among question concepts and answers in KGs. While question concepts ubiquitously present hyponymy at the semantic level, e.g., mammals and animals, this feature is identically reflected in the hierarchical relations in KGs, e.g., a_type_of. Therefore, we are motivated to explore comprehensive reasoning by the hierarchical structures in KGs to help understand questions. However, it is non-trivial to reason over tree-like structures compared with chained paths. Moreover, identifying appropriate hierarchies relies on expertise. To this end, we propose HamQA, a novel Hierarchy-aware multi-hop Question Answering framework on knowledge graphs, to effectively align the mutual hierarchical information between question contexts and KGs. The entire learning is conducted in Hyperbolic space, inspired by its advantages of embedding hierarchical structures. Specifically, (i) we design a context-aware graph attentive network to capture context information. (ii) Hierarchical structures are continuously preserved in KGs by minimizing the Hyperbolic geodesic distances. The comprehensive reasoning is conducted to jointly train both components and provide a top-ranked candidate as an optimal answer. We achieve a higher ranking than the state-of-the-art multi-hop baselines on the official OpenBookQA leaderboard with an accuracy of 85%.Keywords
This publication has 12 references indexed in Scilit:
- Learning Contextualized Knowledge Structures for Commonsense Reasoning2021
- From F to A on the New York Regents Science Exams — An Overview of the Aristo ProjectAI Magazine, 2020
- Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering2020
- Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering2020
- Improving Multi-hop Question Answering over Knowledge Graphs using Knowledge Base Embeddings2020
- Low-Dimensional Hyperbolic Knowledge Graph Embeddings2020
- Improving Natural Language Inference Using External Knowledge in the Science Questions DomainProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Knowledge Graph Embedding Based Question Answering2019
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering2018
- ConceptNet 5.5: An Open Multilingual Graph of General KnowledgeProceedings of the AAAI Conference on Artificial Intelligence, 2017