Entity Attribute Extraction from Unstructured Text with Deep Belief Network

Entity attribute extraction is an extremely challenging research area with broad application prospects. In this paper, we propose a new approach to extract the entities’ attributes from unstructured text corpus that was gathered from Web. The proposed method is an unsupervised machine learning method that extract the entity attributes utilizing DBN. To test the proposed method, we use it to extract attribute in a test corpus, experimental results show that, with our method, entity attributes can be extracted effectively and reduce manual intervention when compared with tradition methods.