Enhancing extraction based summarization with outside word space

Proceedings of the 5th International Joint Conference on Natural Language Processing, pages 1062–1070, Chiang Mai, Thailand, November 8 – 13, 2011. c⃝2011 AFNLP Enhancing extraction based summarization with outside word space Christian Smith, Arne J¨onsson Santa Anna IT Research Institute AB Link¨oping, Sweden christian.smith@liu.se, arnjo@ida.liu.se Abstract We present results from improving vec- tor space based extraction summarizers. The summarizer uses Random Indexing and Page Rank to extract those sentences whose importance are ranked highest for a document, based on vector similarity. Originally the summarizer used only word vectors based on the words in the docu- ment to be summarized. By using a larger word space model the performance of the summarizer was improved. Along with the performance, robustness was improved as random seeds did not affect the summa- rizer as much as before, making for more predictable results from the summarizer. 1 Introduction Many persons have, for various reasons, problems assimilating long complex texts. Not only persons with visual impairments or dyslexia, but also, for instance, those having a different mother tongue or persons in need of a quick summary of a text. A tool for automatic summarization of texts from different genres as an aid in reading can thus be useful for many persons and purposes. Automatic summarization can be done in vari- ous ways. A common distinction is extract versus abstract summaries. An extract summary is cre- ated by extracting the most important sentences from the original text so that the result is a shorter version of the original text with some information still present, for instance the most important sen- tences or words. An abstract summary on the other hand is a summary where the text has been broken down and rebuilt as a complete rewrite to convey a general idea of the original text. Furthermore, the summaries can be indicative (for instance only providing keywords as central topics) or informa- tive (content focused) (Firmin and Chrzanowski, 1999). The former might be more usable when a reader needs to decide whether or not the text is in- teresting to read and the latter when a reader more easily needs to get a grasp of the meaning of a text that is supposed to be read. In this paper we will examine and try to increase the performance of an automatic extraction-based summarizer. Previously, the summarizer has been functioning without aid of outside corpora or train- ing material. While the performance have been good, some improvements utilizing an outside cor- pus can be achieved. The technique behind the summarizer will first be described in more detail, after which some re- sults are presented which indicates that the perfor- mance can be enhanced by using outside training material. 2 The word space model The word space model, or vector space model (Eld´en, 2007), is a spatial representa- tion of a word’s meaning that can reduce the linguistic variability and capture semantically related concepts by taking into account the positioning of words in a multidimensional space, instead of looking at …

Content truncated to 500 words