Abstract

To identify relationships among entities in natural language texts, extraction of entity relationships technically provides a fundamental support for knowledge graph, intelligent information retrieval, and semantic analysis, promotes the construction of knowledge bases, and improves efficiency of searching and semantic analysis. Traditional methods of relationship extraction, either those proposed at the earlier times or those based on traditional machine learning and deep learning, have focused on keeping relationships and entities in their own silos: extracting relationships and entities are conducted in steps before obtaining the mappings. To address this problem, a novel Chinese relationship extraction method is proposed in this paper. Firstly, the triple is treated as an entity relation chain and can identify the entity before the relationship and predict its corresponding relationship and the entity after the relationship. Secondly, the Joint Extraction of Entity Mentions and Relations model is based on the Bidirectional Long Short-Term Memory and Maximum Entropy Markov Model. Experimental results indicate that the proposed model can achieve a precision of 79.2% which is much higher than that of traditional models.