Fig. 1From: CERC: an interactive content extraction, recognition, and construction tool for clinical and biomedical textCERC system diagram. This shows the overall design of CERC. Input text is first preprocessed via segmentation, tokenization, stemming, and controlled dictionary filtering. Extractive summarization is performed using a new algorithm, the MINTS algorithm, a multi-stage algorithm for sentence extraction and ranking. A word-cloud based visualization method is used to represent term/concept distributionBack to article page