Joint Extraction Model of Entity Relations Based on BERT-CRF

Abstract

Entity and relation extraction (ERE) is a major task in information extraction and knowledge mapping. Existing methods usually consider two tasks, named entity recognition (NER) and relation extraction (RE), separately using a pipeline approach, which loses a lot of interaction information between tasks and contextual information of text sequences. In order to settle this problem, this paper proposes an end-to-end entity relation joint extraction method based on the head-entity attention mechanism and fusing contextual semantic features. The overall structure of this method adopts BERT-CRF to decode the header entity and its type, and then uses the header entity information as the Query in the attention mechanism, while fusing entity type label embedding and entity relative position to achieve feature enhancement, which enhances the information interaction between entity model and relational model. In the experiments of the commonly used English dataset NYT and Chinese dataset DuIE, this method has achieved high extraction accuracy and F1 score. It is shown that the model is applicable in both English and Chinese contexts.