How to Get the Same News from Different Language News Papers

摘要

This paper presents an ongoing work on identifying similarity between documents across News papers in different languages. Our aim is to identify similar documents for a given News or event as a query, across languages and make cross lingual search more accurate and easy. For example given an event or News in English, all the English news documents related to the query are retrieved as well as in other languages such as Hindi, Bengali, Tamil, Telugu, Malayalam, Spanish. We use Vector Space Model, a known method for similarity calculation, but the novelty is in identification of terms for VSM calculation. Here a robust translation system is not used for translating the documents. The system is working with good recall and precision.