Joint extraction of entities and relations based on character graph convolutional network and Multi-Head Self-Attention Mechanism
Authors:
- 4 March 2020
- journal article
- research article
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 33 (2) , 349-362
Abstract
The traditional method of extracting entities and relations not only disregards the dependency between the two subtasks of entities and relations but also facilitates the cumulative propagation of errors. To solve these problems, a method – called MSBD – of joint extraction of entities and relations based on the Character Graph Convolutional Network (CGCN) and Multi-Head Self-Attention Mechanism (MS) is proposed. First, a new tagging scheme is used to tag the positions of entities and relations in the text. Second, to depict the hierarchical structure information between the entities and the relations in the text and the internal structure information of the entity, the CGCN is designed to obtain the character vector of the text. MS is introduced into the coding framework of Bidirectional Long Short-Term Memory (BiLSTM) to capture the relative position information between two entities in the text and represent the subspace information. The Dense Connected Convolutional Network (Dense Net) is embedded in the decoding framework to enhance the reuse and transmission of key information and achieve joint extraction of entities and relations in the text. The experimental results show that the P, R and F values are significantly improved for extracting entities and relations.Keywords
Funding Information
- The National Natural Science Foundation of China (61962057, 61662074, 61563051, 61662074, 61262064)
- Xinjiang Uygur Autonomous Region Scientific and Technological Personnel Training Project (QN2016YX0051)
- Xinjiang Tianshan Youth Project (2017Q011)
- Research and Innovation Project of Postgraduate in Autonomous Region (XJ2019G070)
- the Key Project of National Natural Science Foundation of China (61331011)
This publication has 20 references indexed in Scilit:
- Joint entity and relation extraction based on a hybrid neural networkNeurocomputing, 2017
- CoType2017
- A neural joint model for entity and relation extraction from biomedical textBMC Bioinformatics, 2017
- Unsupervised entity and relation extraction from clinical records in ItalianComputers in Biology and Medicine, 2016
- End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures2016
- Investigating LSTMs for Joint Extraction of Opinion Entities and Relations2016
- Neural Architectures for Named Entity Recognition2016
- Supertagging With LSTMs2016
- Improved Relation Extraction with Feature-Rich Compositional Embedding Models2015
- Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths2015