First Classified Annotated Bibliography of NLP Tasks in the Burmese Language of Myanmar

Abstract

Natural Language Processing (NLP) has emerged with a wide scope of research in the area.  The Burmese language, also called the Myanmar Language is a resource scarce, tonal, analytical, syllable-timed and principally monosyllabic language with Subject-Object-Verb (SOV) ordering.  NLP of Burmese language is also challenged by the fact that it has no white spaces and word boundaries.  Keeping these facts in view, the current paper is a first formal attempt to present a bibliography of research works pertinent to NLP tasks in Burmese language.  Instead of presenting mere catalogue, the current work is also specifically elaborated by annotations as well as classifications of NLP task research works in NLP related categories.  In fact, to the best of author’s knowledge, this is first work of its kind worldwide for any language.  For a period spanning more than 25 years, the paper discusses Burmese language Word Identification, Segmentation, Disambiguation, Collation, Semantic Parsing and Tokenization followed by Part-Of-Speech (POS) Tagging, Machine Translation Systems (MTS), Text Keying/Input, Recognition and Text Display Methods.  Burmese language WordNet, Search Engine and influence of other languages on Burmese language are also discussed.