Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering over Knowledge Graphs
Zile Qiao, Wei Ye, Tong Zhang, Tong Mo, Weiping Li, Shikun Zhang
Abstract
Answering natural language questions on knowledge graphs (KGQA) remains a great challenge in terms of understanding complex questions via multi-hop reasoning. Previous efforts usually exploit large-scale entity-related text corpus or knowledge graph (KG) embeddings as auxiliary information to facilitate answer selection. However, the rich semantics implied in off-the-shelf relation paths between entities is far from well explored. This paper proposes improving multi-hop KGQA by exploiting relation paths’ hybrid semantics. Specifically, we integrate explicit textual information and implicit KG structural features of relation paths based on a novel rotate-and-scale entity link prediction framework. Extensive experiments on three existing KGQA datasets demonstrate the superiority of our method, especially in multi-hop scenarios. Further investigation confirms our method’s systematical coordination between questions and relation paths to identify answer entities.- Anthology ID:
- 2022.coling-1.156
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 1813–1822
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.156
- DOI:
- Cite (ACL):
- Zile Qiao, Wei Ye, Tong Zhang, Tong Mo, Weiping Li, and Shikun Zhang. 2022. Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering over Knowledge Graphs. In Proceedings of the 29th International Conference on Computational Linguistics, pages 1813–1822, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- Exploiting Hybrid Semantics of Relation Paths for Multi-hop Question Answering over Knowledge Graphs (Qiao et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.coling-1.156.pdf
- Data
- ComplexWebQuestions, MetaQA, WebQuestionsSP