Abstract
We study the problem of learning to reason in large scale knowledge graphs (KGs). More specifically, we describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector-space by sampling the most promising relation to extend its path. In contrast to prior work, our approach includes a reward function that takes the accuracy, diversity, and efficiency into consideration. Experimentally, we show that our proposed method outperforms a path-ranking based algorithm and knowledge graph embedding methods on Freebase and Never-Ending Language Learning datasets.- Anthology ID:
- D17-1060
- Volume:
- Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
- Month:
- September
- Year:
- 2017
- Address:
- Copenhagen, Denmark
- Editors:
- Martha Palmer, Rebecca Hwa, Sebastian Riedel
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 564–573
- Language:
- URL:
- https://aclanthology.org/D17-1060
- DOI:
- 10.18653/v1/D17-1060
- Cite (ACL):
- Wenhan Xiong, Thien Hoang, and William Yang Wang. 2017. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 564–573, Copenhagen, Denmark. Association for Computational Linguistics.
- Cite (Informal):
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning (Xiong et al., EMNLP 2017)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/D17-1060.pdf
- Code
- xwhan/DeepPath + additional community code
- Data
- NELL-995, NELL