Jason Coleman's Thesis Wiki
old stuff below this line
Topic
Automated Text Summarization and Sentence Generation (proposal: JasonTopicProposal)Idea
Most text summarization systems are designed for use in the summarization of news articles or academic essays, or for use in other limited domains. A few systems, including Discourse Parsing, are presented as “general purpose” summarizers, though the success these systems vary over any given domain. To my knowledge, no summarization system has been designed specifically for use by creative writers (or in the analysis of fiction). In fact, there is a general lack of word-processing and investigatory tools which have been designed with the creative writer in mind. In this thesis, I wish to do a comparative analysis over a wide sampling of summarization systems and techniques in order to report on the state of the art in this field and determine how these systems might be applicable for use in creative writing.Reading List
Cols Random Sentence Generator: http://www.ast.cam.ac.uk/~cmf/generateHovy, Eduard & Lin, Chin-Yew (2001). Automated Text Summarization and the Summarist System.
Hovy, Eduard & Marcu, Daniel (1998). COLING-ACL ‘98 Pre-Conference Tutorial (Power Point presentation).
Julian Kupiec, Jan Pedersen, & Francine Chen (1994). A Trainable Document Summarizer.
Mani, Inderjeet (2001). Summarization Evaluation: An Overview.
Mani, Inderjeet (Editor) & Maybury, Mark T. (Editor) (1999). Advances in Automatic Text Summarization.
Marcu, Daniel (2000). The Theory and Practice of Discourse Parsing and Summarization. (JasonDiscourseParsingNotes)
Matthiessen, Christian (and others) (1997). The Multex generator and its environment: application and development.
Ulf Hermjakob, Eduard Hovy, & Chin-Yew Lin (2002). Automated Question Answering in Webclopedia- A Demonstration.
