Using Roget's Thesaurus to Determine the Similarity of Texts

The book "Using Roget's Thesaurus to Determine the Similarity of Texts" by Jeremy Ellman offers a comprehensive examination of extracting meaning representations from text content. It presents an innovative approach that utilizes Roget's Thesaurus as an external knowledge source to analyze texts of any length and complexity. The developed method allows for the assessment of similarity between different texts by identifying the lexical chains contained within them. These chains consist of meaning-related sequences of words determined by simple relationships between the thesaurus entries. Thus, the book provides valuable insights into text analysis and the evaluation of text similarities, which is significant for researchers and practitioners in the fields of linguistics and computer science.