Open Entity Semantic Relation Extraction in Big Data Environment

Aiming at the problem that traditional entity relationship extraction needs to define a comprehensive entity relationship type system, poor portability, and the inability to process massive Internet texts, an open Chinese entity relationship extraction method based on CRFs(Conditional random fields) is proposed. At the same time, due to the limited computing resources of a single machine, an open entity relationship extraction method based on the Hadoop distributed computing framework is proposed. Experiments show that the CRFs model with syntactic parse tree has improved accuracy and recall in the entity relationship extraction task; this paper also designed an experiment to compare the entity relationship extraction based on the Hadoop distributed computing framework with the stand-alone version. The experiment shows that the former extraction effect is better.