Towards Constructing a Chinese Information Extraction System to Support Innovations in Library Services

Being aware of the importance of Information Extraction (IE) in supportinginnovation in many areas of library services, the authors began toconstruct a Chinese information extraction system to effectively processhuge Chinese information resources. The authors bring forth a Chinese IEsolution which makes full use of the GATE (General Architecture for TextEngineering) system from the University of Sheffi eld, trying to develop aChinese IE plug-in to process Chinese information resources based onthe GATE framework. The article analyses the framework of the GATEsystem, describes the Chinese IE solution based on the GATE systemand focuses on three key diffi culties in the process of implementing aChinese information extraction system. These are: 1. Chinese tokenizingproblem; 2. professional gazetteers; 3. Chinese named entity recognition.The authors have successfully implemented this system and carried outan experiment in which the Chinese IE system successfully extractedthousands of pieces of science and technology news. The authors believethis system is a signifi cant trial and lays a good foundation for futureresearch work.