A Review on Entity Relation Extraction

Because of large amounts of unstructured data generated on the Internet, entity relation extraction is believed to have high commercial value. Entity relation extraction is a case of information extraction and it is based on entity recognition. This paper firstly gives a brief overview of relation extraction. On the basis of reviewing the history of relation extraction, the research status of relation extraction is analyzed. Then the paper divides theses research into three categories: supervised machine learning methods, semi-supervised machine learning methods and unsupervised machine learning method, and toward to the deep learning direction.