Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks
Rajarshi Das, Arvind Neelakantan, David Belanger, Andrew McCallum
Abstract
Our goal is to combine the rich multi-step inference of symbolic logical reasoning with the generalization capabilities of neural networks. We are particularly interested in complex reasoning about entities and relations in text and large-scale knowledge bases (KBs). Neelakantan et al. (2015) use RNNs to compose the distributed semantics of multi-hop paths in KBs; however for multiple reasons, the approach lacks accuracy and practicality. This paper proposes three significant modeling advances: (1) we learn to jointly reason about relations, entities, and entity-types; (2) we use neural attention modeling to incorporate multiple paths; (3) we learn to share strength in a single RNN that represents logical composition across all relations. On a large-scale Freebase+ClueWeb prediction task, we achieve 25% error reduction, and a 53% error reduction on sparse relations due to shared strength. On chains of reasoning in WordNet we reduce error in mean quantile by 84% versus previous state-of-the-art.- Anthology ID:
- E17-1013
- Volume:
- Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
- Month:
- April
- Year:
- 2017
- Address:
- Valencia, Spain
- Editors:
- Mirella Lapata, Phil Blunsom, Alexander Koller
- Venue:
- EACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 132–141
- Language:
- URL:
- https://aclanthology.org/E17-1013
- DOI:
- Cite (ACL):
- Rajarshi Das, Arvind Neelakantan, David Belanger, and Andrew McCallum. 2017. Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 132–141, Valencia, Spain. Association for Computational Linguistics.
- Cite (Informal):
- Chains of Reasoning over Entities, Relations, and Text using Recurrent Neural Networks (Das et al., EACL 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/E17-1013.pdf
- Code
- additional community code