Syllable Segmentation

Syllable segmentation is the process of determination of syllable boundaries in a piece of text. Since Burmese is the tonal and analytic language and Burmese writing system is a syllabic writing system, the fundamental building blocks of a language are the syllables. In determination of syllable boundaries in Burmese Script, there can be of two types; 1) phonological boundary of a syllable, and 2) orthographic boundary of a syllable. Since Burmese script is a phonetic script, the phonological segmentation of a syllable is the basic segmentation. The phonological boundary of a syllable is defined, as the name goes, according to the phonological manner whereas the orthographic boundary of a syllable is defined according to the orthography. The orthographic syllable need not correspond exactly with a phonological syllable. The orthographic syllable is just the combination of phonological syllables and the non-breaking rules. Example: In a မႏၱေလး word, it has 3 phonological syllables, မန္, တ and ေလး. But, for orthographic syllable, it has just 2 syllables, မႏၱ and ေလး .

References

For all of you to have a reference for future NLP works, I uploaded some of my academic publications.

Master Thesis at Nagaoka University of Technology

Languages of Myanmar In Cyberspace

Word Break

A word, is a unit of language, carries meaning and consists of one or more morphemes. Although there are spaces to separate between words English, no spaces are needed to add in Myanmar. Typically, a word will consist of a root or stem and zero or more affixes. Words can be combined to create phrase, clauses and sentences (Wikipedia).

So, word boundary must be detected for Myanmar Language. But, Myanmar Language is the tonal and analytic language. Myanmar writing system is a syllabic writing system, so the fundamental building blocks of a language are the syllables. Determining syllable boundary can be done by rule base.

A word can be formed by one or more than one syllables.

Syllable break which can be used for sorting, searching, text to speech, transliteration, can also be used for word breaking methods.

Word break which can be used for spell checking, grammar checking, translation, line breaking, etc,.

Our Discussion group

We have created a google group for discussion about Myanmar NLP development. I like to invite all the interested people to join and post at myanmarnlpteam@googlegroups.com.

What is Font?

Some people put messages about "FONT". So, I like to contribute some information on "FONT". The interested people can learn about "FONT" at the following sites:
w3 (World Wide Web Consortium) says as http://www.w3.org/TR/REC-CSS2/fonts.html
wiki (The free encyclopedia) says as http://en.wikipedia.org/wiki/Font

I like to let people know that font is not to sort, break, etc. The background encoding has to be used for syllable break, sorting, word breaking, etc.

In Myanmar, there are many magicians. The magicians use technology to show magic to people. So, people think it is true.

I like to give a general logic here.
1 ft= 12 x 1 inch
so 12 times of 1 in (from Myanmar) has to be the same with 1 ft (from United States). Am I right?

It is called "STANDARD". If "SORTING" is OK, all Unicode encoded text can be sorted. Why it is only for the specific "FONT" and any product. It is like 12 times of 1 in (from Myanmar) is not equal to 1 ft (from United States).

It is also the same for "BREAK" and other processes.

Unicode Font (OR) Unicode Compliant Font

Unicode consortium do not develop any font. The font developers develop font. There can be Unicode compliant fonts and Unicode non-compliant fonts. If someone wants to sure that the font is Unicode compliant or not, check with the Unicode system.
Myanmar 3, the latest release of our NLP research team, is the Unicode compliant font. The main reason Myanmar 3 is reliable and Unicode compliant is that the Unicode system for Myanmar is created with us.

Download Links

We provide some downloads which are the products of our team. These products (softwares, fonts, publications, documents, etc) are created by all or one of the members of Myanmar NLP research center.
(Point the cursor on the following links. Right click on the mouse, choose "save target as".)
Myanmar 3 Font and Keyboard
Myanmar 3 Font Only