HfGCN: Hierarchical fused GCN for Joint Entity and Relation Extraction
- 1 December 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 307-314
Abstract
The extraction of entities and relations from un-structured text is crucial for information extraction. The joint models have been proposed to solve both tasks simultaneously. However, previous work only focuses on the linear representation of sentences and neglects hierarchical grammatical knowledge, which can be injected into the word representations to improve the accuracy of joint extraction. In this paper, we propose a joint model, integrating the fused syntax graph information into a hierarchical graph convolution model for joint extraction. Specifically, we use the attention mechanism to mine the implicit relations between words and dynamically fuse it with explicit dependency syntax graph to obtain fused graph, and through hierarchical graph convolution network to obtain the fused features of different granularity. Experimental results show that our model yields a significant performance compared with prior strong baselines in two datasets.Keywords
This publication has 18 references indexed in Scilit:
- Neural Relation Extraction within and across Sentence BoundariesProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Joint entity recognition and relation extraction as a multi-head selection problemExpert Systems with Applications, 2018
- Adversarial training for multi-context joint entity and relation extraction2018
- Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction2018
- Long short-term memory RNN for biomedical named entity recognitionBMC Bioinformatics, 2017
- Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees2017
- End-to-End Neural Relation Extraction with Global Optimization2017
- Named Entity Recognition with Bidirectional LSTM-CNNsTransactions of the Association for Computational Linguistics, 2016
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures2016
- Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reportsJournal of Biomedical Informatics, 2012