Extractive Summarization for Myanmar Language

Due to increasing availability of online information, tools and mechanisms for automatic summarization of documents is needed. Text summarization is currently a major research topic in Natural Language Processing. There are various approaches to generate text summary. Among them, we proposed Myanmar text summarization using latent semantic analysis (LSA). Latent semantic analysis (LSA) is a technique in natural language processing,and can analyze relationships between a set of documents and the terms they contain by producing a set of concepts related to the documents and terms. It is an unsupervised approach which does not need any traning or external knowledge. There is no LSA based sentence extraction in Myanmar language. This is the first LSA based Text Summarizer in Myanmar. This paper present generic, extractve and single-document Myanmar text summarization using latent semantic analysis. This paper compare two sentence selection methods (Steinberger and Jezek's approach and Ozay approach) of latent semantic analysis to extract important sentences. We summarize Myanmar news from Myanmar official websites such as 7day daily, iyarwaddy, etc.