Myanmar news summarization using different word representations

There is enormous amount information available in different forms of sources and genres. In order to extract useful from a massive data, automatic mechanism required. The text summarization systems assist with content reduction keeping the important filtering non-important parts text. Good document representation really get relevant information. Bag-of-words cannot give word similarity on syntactic semantic relationship. Word embedding can good capture encode relation between words. Therefore, centroid based employed this paper. Myanmar news proposed. paper, local international are summarized using centroid-based summarizer effectiveness approach, embedding. Experiments were done dataset models results compared performance bag-of-words summarization. Centroid performs comprehensively better than bag-of-words.