Knowledge Extraction

We research on how to automatically extract language knowledge and common sense. We expect that the language processing technology and the acquired knowledge can automatically analyze a large amount of text in the Internet and extract knowledge from it. Knowledge construction is a time-consuming and labor-intensive project. We have developed the Chinese processing infrastructure in the past two decades to lay the foundation for future automated knowledge construction. These infrastructures include annotated corpus, sentence structure tree databases, Chinese grammar and lexical analysis systems, and sentence parsers. We use the completed basic knowledge and technology to automatically extract the hidden information in network files, expand the existing knowledge structure and build a domain knowledge base and a vocabulary knowledge base. We connect different knowledge bases to form a complete concept network to improve computer reasoning and language understanding.