Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks
This paper addresses the problem of inferring the fine-grained type of an entity from a knowledge base. We convert this problem into the task of graph-based semi-supervised classification, and propose Hierarchical Multi Graph Convolutional Network (HMGCN), a novel Deep Learning architecture to tackle this problem. We construct three kinds of connectivity matrices to capture different kinds of semantic correlations between entities. A recursive regularization is proposed to model the subClassOf relations between types in given type hierarchy. Extensive experiments with two large-scale public datasets show that our proposed method significantly outperforms four state-of-the-art methods.
- Published in:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) - Type:
Inproceedings - Authors:
H. Jin, L. Hou, J. Li, T. Dong - Year:
2019
Citation information
H. Jin, L. Hou, J. Li, T. Dong: Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks, Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, http://dx.doi.org/10.18653/v1/D19-1502, Jin.etal.2019,
@Inproceedings{Jin.etal.2019,
author={H. Jin, L. Hou, J. Li, T. Dong},
title={Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks},
booktitle={Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
journal={Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
url={http://dx.doi.org/10.18653/v1/D19-1502},
year={2019},
abstract={This paper addresses the problem of inferring the fine-grained type of an entity from a knowledge base. We convert this problem into the task of graph-based semi-supervised classification, and propose Hierarchical Multi Graph Convolutional Network (HMGCN), a novel Deep Learning architecture to tackle this problem. We construct three kinds of connectivity matrices to capture different kinds of...}}