My current research interests cover the following areas related to natural language processing (NLP):

1. Information Extraction, particularly semantic relation extraction, i.e., identifying various relationships between named entities from natural language text;

2. Text Ming in biomedical literature, particularly, the application of information extraction technology in the news domain to Protein-Protein Interaction (PPI) extraction, CDR (Chemical-Disease Relation extraction), and biomedical event extraction etc.;

3. Bilingual resource processing, currently we have finished building an instance-level Chinese-English parallel corpus, and further work is to exploit the corpus in supervised and semi-supervised relation extraction;

4. Social network mining or building social networks, including persons and relationships between them, from free text such as Wikipedia pages rather than from semi-structure text such as those in Wikipedia;

5. Knowledge discovery and its applications, constructing domain-specific knowledge repository using NLP techniques and performing intelligent tasks, such as Information Retrieval (IR), Question Answering (QA) and knowledge inference etc.