Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs

Wenpeng Yin, Yadollah Yaghoobzadeh, Hinrich Schütze


Abstract
Large scale knowledge graphs (KGs) such as Freebase are generally incomplete. Reasoning over multi-hop (mh) KG paths is thus an important capability that is needed for question answering or other NLP tasks that require knowledge about the world. mh-KG reasoning includes diverse scenarios, e.g., given a head entity and a relation path, predict the tail entity; or given two entities connected by some relation paths, predict the unknown relation between them. We present ROPs, recurrent one-hop predictors, that predict entities at each step of mh-KB paths by using recurrent neural networks and vector representations of entities and relations, with two benefits: (i) modeling mh-paths of arbitrary lengths while updating the entity and relation representations by the training signal at each step; (ii) handling different types of mh-KG reasoning in a unified framework. Our models show state-of-the-art for two important multi-hop KG reasoning tasks: Knowledge Base Completion and Path Query Answering.
Anthology ID:
C18-1200
Original:
C18-1200v1
Version 2:
C18-1200v2
Volume:
Proceedings of the 27th International Conference on Computational Linguistics
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Emily M. Bender, Leon Derczynski, Pierre Isabelle
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2369–2378
Language:
URL:
https://aclanthology.org/C18-1200
DOI:
Bibkey:
Cite (ACL):
Wenpeng Yin, Yadollah Yaghoobzadeh, and Hinrich Schütze. 2018. Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs. In Proceedings of the 27th International Conference on Computational Linguistics, pages 2369–2378, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
Recurrent One-Hop Predictions for Reasoning over Knowledge Graphs (Yin et al., COLING 2018)
Copy Citation:
PDF:
https://aclanthology.org/C18-1200.pdf