Hybrid BiLSTM-Siamese Network for Relation Extraction

Relation extraction is an important processing task in knowledge graph completion. In previous approaches, it is considered to be a multi-class classification problem. In this paper, we propose a novel approach called hybrid BiLSTM-Siamese network which combines two word-level bidirectional LSTMs by a Siamese model architecture. It learns a similarity metric between two sentences and predicts the relation of a new sentence by k-nearest neighbors algorithm. In experiments, we use the SemEval-2010 Task8 dataset and achieve an F1-score of 81. 8%.

Authors

• Zeyuan Cui Shandong University
• Li Pan School of Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China Shanghai Key Laboratory of Integrated Administration Technologies for Information Security, Shanghai 200240, China Zhangjiang Institute for Advanced Study, Shanghai 201203, China
• Shijun Liu School of Software, Shandong University Dareway Software Co., Ltd

Keywords

• Siamese Network
• Relation Extraction
• Knowledge Graph