Algorithm to Resolve Anaphoric Ambiguity of Text Summarization

Abstract

Automatic text summarization aims to address the information overload problem due to the availability of enormous amount of information on World Wide Web, by generating summary of the documents. A summary is a text that is produced from one or more texts, that contain only the significant information contents of the original text(s), and that is no longer than half of the original text. Text summarization can be classified into two categories: abstractive and extractive summarization. An extractive summary is simply a subset of the sentences in the original text, it generally uses statistical methods to generate summary. These summaries do not guarantee a good narrative coherence, but they can conveniently represent an approximate content of the text. In abstractive text summarization, first the text is understood using linguistic methods and then the main concepts are expressed in natural language, using new concepts and expression to best describe the most important information present in the original text document. In this Thesis, a survey on extractive text summarization techniques has been presented and work is done to resolve anaphoric problems in text summarization.