User:Mohitraj

From Apertium
Jump to navigation Jump to search


== Apertium GSOC 2019

Morphological Analyzer of Magahi ==


Contact Information

Name: Mohit Raj

E-mail address: mohiitraj@gmail.com

Mobile Number : +91 9304843938(India)

IRC Nick: mohitraj

Github: Mohit-Raj123

Timezone: UTC +5.30



Why is it that you are interested in Apertium and Machine Translation ?

I belong to India where 22 shedule language and and almost 100 non-scheduled languages. It is obtained by subsuming several distinct languages under ‘dialects’ of some of the majority languages; languages with less than 10000 speakers are not even recognised and are put under a category called ‘others’. I like the concept of Apertium as an open source language translator that is really a nice thing to the world that would be definitely helpful for students, organinzation and any other body who wants to do work in the field of Machine Translation. My interest in Apertium because it is not only machine translation, but also free resources that can be used for other purposes e.g. dictionary, morphological analyser and spell checkers etc. I am student of Linguistics and My area of interest is Machine Translation and Natural Language Processing. Previously i have completed courses on XML, Python programming, Language Technologies and Machine Translation. I have worked towards the development of parser for Magahi, in collaboration with my classmate Neerav Mathur, for course projects.I took participation in following workshop :-


1. 9th IASNLP-2018: IIIT-Hyderabad Advanced School on Natural Language Processing

2. SOIL-Tech: Towards Digital India at JNU, New Delhi

3. Hands on workshop on Statistical Machine Translation with Moses at K.M.I, Agra


I wants to work on marginalised language because it will be definitely helpful to develop tools and technology for marginalised language that would be quite helpful to preserve language heritage of India and the world.



My Proposal

Title

Morphological analyzer of Magahi


== Why Google and Apertium should sponset it ? ==

Many language pairs are available on Apertium but many have to be develop. One of those is Eng-Magahi pair for Machine translation that should be develop. In the machine translation Morphological Analyzer plays an important role in improving the system’s performance for morphologically rich language like Magahi. So I am interested in developing morph analyzer of Magahi. How and who it will benefit in society ?

There are almost 12.7 million native speaker of Magahi accordingto census of 2011 and aditional speakers counted under Hindi. Eng-Magahi MT would be quite helpful for Magahi users and it would also play an important role in preserving the marginalised language.

Work Plan

Week1

Preparing linguistic rule for Morphological analyzer


Week2

Continue....


Week3

Tokenizing the data


Week4

Preparing the tagset


Deliverable #1

Submit the Tokenized and prepared tagset


Week5

Preparing the affix list


Week6

Writing the programm to develop Magahi morphological analyzer


Week7

Continueing programming


Week8

Train and test the model


Deliverable #2

Submit the program and trained, test model


Week9

Test the model with different domain of word


Week10

Fixing the occurring error in model

Week11

Again train and test the model


Week12

Evaluation of results or model

Project Completed

Submission of project