Abstract:
Part-of-Speech tagging is the process of
marking up the words in a text as corresponding
to a particular part of speech based on both its
definition, as well as its context. Tagsets and
word disambiguation rules are fundamental
parts of any POS tagger. This system proposed a
new approach to POS tagger of Myanmar text. It
exploits a hybrid approach which is combination
of rule based and statistical methods to tag
Myanmar sentence. The tagger of this system
demonstrates on the following ideas: (i) Design
detail tagsets for Part-of-Speech according from
Myanmar Grammar. (ii) Generate rules for
disambiguation of word in various part of speech
according to different morphological structure.
(iii) Explicit use of both preceding and following
contexts via a cyclic dependency network
representation. So, the expected results of this
proposed system shows that tagging accuracy is
high by using morphological structure of
Myanmar Language.
