Abstract:
Named Entity Identification includes locating named entities and classifying those names in text. NEI is an important task in NLP applications such as Information Extraction, Cross Language information Retrieval, Question Answering, and Machine Translation. In this paper, we presented a method for Myanmar Named Entity Identification using hybrid method. A hybrid method is a combination of ruled based and statistical N-grams based method which use name databases. We have examined a sample of 10 Myanmar text files .We obtained 89% of accuracy in Named Entity Identification. We also classified those named entities into three classes. After that, those names are transliterated to their relevant Myanmar phonetics. We have used transliteration table for mapping with English word. In transliteration table, Myanmar syllables are transliterated into English pronunciation. The system is implemented using Java.
