Research Article
Fusing BERT and BiLSTM Model to Extract the Weaponry Entity
@INPROCEEDINGS{10.1007/978-3-030-77428-8_8, author={Haojie Ge and Xindong You and Jialai Tian and Xueqiang Lv}, title={Fusing BERT and BiLSTM Model to Extract the Weaponry Entity}, proceedings={Tools for Design, Implementation and Verification of Emerging Information Technologies. 15th EAI International Conference, TridentCom 2020, Virtual Event, November 13, 2020, Proceedings}, proceedings_a={TRIDENTCOM}, year={2021}, month={5}, keywords={Weaponry entity extraction BERT BILSTM Word conversion rate vector Hierarchical entity extractor}, doi={10.1007/978-3-030-77428-8_8} }- Haojie Ge
Xindong You
Jialai Tian
Xueqiang Lv
Year: 2021
Fusing BERT and BiLSTM Model to Extract the Weaponry Entity
TRIDENTCOM
Springer
DOI: 10.1007/978-3-030-77428-8_8
Abstract
Weaponry entity extraction is an indispensable link in the process of constructing a weaponry knowledge graph. In terms of entity extraction of weapons and equipment, a fusion model of domain BERT model and BILSTM model with embedded word vectors and word conversion rate vectors is proposed to identify weapons and equipment entities. First, the BERT model is used to perform pre-training tasks on massive weaponry corpus. Secondly, the Word2vec model is used to train the word vectors to provide a priori semantic information, and the word conversion rate vector is embedded to input more a priori information to the model. Finally, the hierarchical entity extractor extracts entities of different categories. Experiments results show that the fusion model has strong coding ability and sufficient prior knowledge, and the F1 value on the Global Military Network corpus reaches 91.436%.
