Five main research areas in CHIME

• Text Processing
  In CHIME, we investigate various machine learning techniques in text processing, leveraging from the availability of large text corpora as training data. Our text processing research includes text categorization, information extraction, word sense disambiguation, co-reference resolution, etc. In recent years, we have worked on biomedical text such as those related to protein-protein interactions.
• Document Analysis
  Document Analysis pertains to the processing and understanding of the contents of document, particularly in the form of images that are not readily understood by the computer. Our research in document analysis include restoration of distorted document images to facilitate character recognition, text recognition directly from distorted documents without restoration, scientific charts recognition, historical handwritten documents with ink-bleed problems, etc.
• Image Mining
  Image mining deals with the extraction of knowledge, image data relationship, or other patterns not explicitly stored in the images. The image mining research in CHIME focuses on medical images, particularly retina images and brain CT scan images. The main objective is to allow the machine to capture salient features in such images with the view to mine useful information pertaining to medical anomalies.
• Digital Libraries
  Digital libraries aim to transform the way knowledge is created, transmitted and stored. It is a diverse area with contributors from library sciences, databases, natural language processing, multimedia and information retrieval. Our current research applies techniques in machine learning, natural language processing and image processing to develop techniques for information retrieval from digital libraries.
• Medical Information Management
  Our research in medical information management draws from expertise in the medical computing group in the school. Computational technologies for uncertainty management are developed for medical decision modeling. A recent work is to examine information retrieval and automated report generation with respect to radiology CT scan image interpretation.