Morphology is the part of linguistics that deals with the study of words, their internal structure and syntactically their meanings. A Morphological Analysis is the process of providing grammatical information of a word by detecting its morphemes. A morphological analysis generally consists of following information:
These are the very basics of linguistics which lays ground to many other applications. There are various different tools and resources available for morphology analysis of popular languages such as English, but morphological analysis of Nepali texts had been in a shadow for long. Fortunately, the need of these analysis has slowly been recognized.
There has been remarkable developments in Nepali Linguistics in the past 6-7 years, especially from projects at Madan Puraskar Pustakalaya, Nepal.
Projects such as "Dobhase", an english to nepali translator, Spell Checker for Nepali Language, Text-to-Speech for Nepali, has encouraged the development of works in Nepali linguistics. There also has been researches on projects to build a "Morphology Analyzer" for Nepali text as well. "A Morphological Analyzer and a stemmer for Nepali" is a paper by Prof Bal Krishna Bal and Prajol Shrestha, K.U. /Madan Puraskar Pustakalaya, Nepal, and based on the paper I also tried to develop a simple Morpho-Analyzer of Nepali text.
The morpho-analyzer I developed is a derivate of the paper. Link here I used a small set of POS-tag to begin with and small list of Prefixes and Suffixes good enough to test the analyzer. As in the paper, I used XML for the output of the result.
Below are some of the snapshots:
Word segmentation
Part-of-speech tagging
Lemmatization
These are the very basics of linguistics which lays ground to many other applications. There are various different tools and resources available for morphology analysis of popular languages such as English, but morphological analysis of Nepali texts had been in a shadow for long. Fortunately, the need of these analysis has slowly been recognized.
There has been remarkable developments in Nepali Linguistics in the past 6-7 years, especially from projects at Madan Puraskar Pustakalaya, Nepal.
Projects such as "Dobhase", an english to nepali translator, Spell Checker for Nepali Language, Text-to-Speech for Nepali, has encouraged the development of works in Nepali linguistics. There also has been researches on projects to build a "Morphology Analyzer" for Nepali text as well. "A Morphological Analyzer and a stemmer for Nepali" is a paper by Prof Bal Krishna Bal and Prajol Shrestha, K.U. /Madan Puraskar Pustakalaya, Nepal, and based on the paper I also tried to develop a simple Morpho-Analyzer of Nepali text.
The morpho-analyzer I developed is a derivate of the paper. Link here I used a small set of POS-tag to begin with and small list of Prefixes and Suffixes good enough to test the analyzer. As in the paper, I used XML for the output of the result.
Below are some of the snapshots:
 |
| Morpho Analyzer |
 |
| XML output |
I am hoping to build this up and work on methodologies to improve what I have today.
Any update on this project? Stemming for Nepali language is becoming important in many fields.
ReplyDeleteWe are working on similar kind of project in Sikkim Manipal University.
ReplyDeleteNice blog and we know that 2015 is huge disaster year for Nepal and then Patanjali rahat kosh has been made to work Nepal tarsdi help in that Furthermore This Trust did a recognizable work for Nepal earthquake victims.For more information please visit our site: - nepal trasdi
ReplyDeleteNice blog and year 2015 is very difficult for Nepal people's and Patanjali yogpeeth Nepal trust is provide help for Nepal earthquake victims. For more information Please visit site: - patanjali Disaster Management
ReplyDeletethanks for this article
ReplyDeleteBy the way, you may also use electronic data room for your goals. I suppose that this info might be very useful for you.
ReplyDeleteBy the way,
ReplyDelete