ModDBS-X : A Diversity Based Summarizer for DUC2001

1 Description of the system ModDBS-X is a clustering based single document summarizer. It is an open-domain extractive summarizer, demanding of the input nothing more than the availability of basic IR statistics such as term and document frequency. Therefore it could be adapted for any language and domain without much effort. The system goes through three major states to generate a summary: data preparation, summarization, and post-summarization. An input text is first examined for its conformity to the XML syntax; some portions of it are extracted for use in summarization, which are passed on to the sentence selection step, which in turn builds diverse topical clusters over the input and chooses representative sentences thereof. The selected sentences are then put through a post-summarization process, where parenthetical expressions are identified and removed.