Analysis of BMW Model for Title Word Selection on Indic Script

A title is a short summary that represents document's main theme. Title can help the reader to have the main idea without reading the entire document. To generate a title for a document, we have to select appropriate words as title words and put them in sequence. The process of generating title for a given document by using machine, can be done by using summarization approaches or by using Statistical approaches or by combing both. For a given document, selecting appropriate words for generating a title by using any available approach mainly depends on the characteristics of the language. In this paper ,we have examined the influence of the language characteristics in the process of title word selection by using the Naïve Bayes probabilistic approach ( called BMW Model ) on the documents which are available in the language ' Telugu '. And also we have investigated the influence of word weight for the selection of title words in BMW Model. By using F1 metric, we have evaluated the title word selection process.