Difference between revisions of "User:Ifeanyi/proposal"

From Apertium
Jump to navigation Jump to search
 
(43 intermediate revisions by 2 users not shown)
Line 1: Line 1:
<b>GSOC 2021: Create a usable version of these language pair: English--Igbo</b>

== CONTACT INFORMATION ==
== CONTACT INFORMATION ==
<p>'''Name:''' Okonkwo Ifeanyichukwu </p>
<p>'''Name:''' Okonkwo Ifeanyichukwu </p>
Line 5: Line 7:
<p>'''E-mail:''' ifeanyijasper11@gmail.com</p>
<p>'''E-mail:''' ifeanyijasper11@gmail.com</p>
<p>'''IRC:''' ifeanyi</p>
<p>'''IRC:''' ifeanyi</p>
<p>'''Timezone:'''GMT +1</p>
<p>'''Timezone:''' GMT +1</p>
<p>'''Github:'''https://github.com/Ifeanyijasper/</p>
<p>'''Github:''' https://github.com/Ifeanyijasper/</p>


== Why is it that you are interested in Apertium? ==
== Why is it that you are interested in Apertium? ==
Apertium is a free and open-source translation machine and I have passion for machine learning and data science. I got to know about apertium through a friend who is a member of the organisation. Communication which is one of its kind is so welcoming i.e. everyone is willing to provide you a solution in case if you are stuck in a particular issue. I love Igbo language so much that am willing to get involve or participate in anything that concerns it.


== Which of the published tasks are you interested in? What do you plan to do? ==
== Which of the published tasks are you interested in? What do you plan to do? ==
=== Apertium translation pair for English and Igbo ===
I am interested in adding a new language pair that is [http://wiki.apertium.org/wiki/Ideas_for_Google_Summer_of_Code#Create_a_usable_version_of_one_of_these_language_pairs:_English--Igbo.2C_English--Yoruba.2C_English--Tigrinya.2C_English--Swahili.2C_English-Hausa English-Igbo].

=== Why google should sponsor it?===
<p>Nigeria is a big country with a large population that attracts tourists and immigrants. On staying in the country 45% of people will tend to learn the native languages; of which Ibo is very popular among Nigeria's languages. Translating Apertium to ibo will go a long way, though indirectly to preserve Nigeria's rich culture. The language will be encouraged because tools like apertium will be available for people to use on the internet.</p>
<p>In the 21st-century apertium incorporating ibo as one of its languages will help in one way or the other to encourage other countries to easily interact with Igbo people.
Most of the time whenever we travel anywhere in the world we meet at least one Nigerian and the communication would likely be in our Native language since it helps us feel we are in our homeland.
In some rural areas in Nigeria, people speak only Igbo and if these places are visited by tourist they might need translation to English to communicate</p>


== Coding Challenge ==
== Coding Challenge ==
Line 16: Line 27:
<p>1. Installed Apertium and necessary tools.</p>
<p>1. Installed Apertium and necessary tools.</p>
<p>2. Add some words to bidix and ibo.lexc file.</p>
<p>2. Add some words to bidix and ibo.lexc file.</p>
<p>3. Translated some words from this story as much as possible.</p>
<p>3. Translated some words from [https://sourceforge.net/p/apertium/svn/HEAD/tree/branches/xupaixkar/rasskaz/en.txt this story] as much as possible.</p>
<p>4. Push changes to the main git repository. [https://github.com/Ifeanyijasper/apertium-eng-ibo eng-ibo] and [https://github.com/Ifeanyijasper/apertium-ibo ibo]</p>
<p>4. Pushed into the main git repo.</p>


== MILESTONES ==
== MILESTONES ==
Line 32: Line 43:


'''Week 1: '''
'''Week 1: '''
Performing analysis of ibo morphology.
Improving Igbo monolingual dictionary
Adding more words to ibo.lexc file..
Adding nouns,prepositions,adjectives to bilingual dictionary


'''Week 2: '''
'''Week 2: '''
Analysis and generation of those added words.
Adding verbs,pronouns conjunctions to bilingual dictionary
Write transfer rules for verbs and noun
'''Week 3: '''
'''Week 3: '''
Continue with the work.
Continue with the work.
Adding verbs and more nouns from English Wiktionary

'''Week 4: '''
'''Week 4: '''
Testvoc for closed-classes.
Update documentation
Preparing for evaluation.
Preparing for evaluation.


<p>'''Outcome:''' Kannada monolingual dictionary takes action.</p>
<p>'''Deliverable 1:''' Bilingual dictionary, basic transfer rules.</p>




Line 53: Line 64:


'''Week 5: '''
'''Week 5: '''
Observing the sentence structure of both the languages.
Observing the sentence structure of both languages.
Fixing minor issues in Marathi dictionary.
Fixing minor issues in Ibo dictionary.


'''Week 6: '''
'''Week 6: '''
Adding words to the bilingual dictionary.
Adding words to the bilingual dictionary.
Adding words with tone markings.


'''Week 7: '''
'''Week 7: '''
Continue adding words with tone markings.
Including transfer rules.
Including transfer rules.


Line 66: Line 79:
Test translation and prepare for evaluation.
Test translation and prepare for evaluation.


<p>'''Outcome:'''Understandable translation between these two languages.</p>
<p>'''Deliverable 2:'''Understandable translation between these two languages.</p>




Line 74: Line 87:


'''Week 9: '''
'''Week 9: '''
Extend bilingual dictionary.

Disambiguation rules and discourse structure for Kannada.
Work on disambiguation rules.


'''Week 10: '''
'''Week 10: '''
Constraint grammar and tagger training.
testvoc and improvements.
More work on transfer rules.


'''Week 11: '''
'''Week 11: '''
Continue with the work. Testing using corpus or newspaper contents.
Continue with the work. Testing using newspaper contents.


'''Week 12: '''
'''Week 12: '''
Writing documentation, complete testing and fixing bugs.
Writing documentation, complete testing and fixing bugs.

<p>'''Outcome:''' Hopefully a testvoc clean pair for release.</p>




Line 92: Line 104:


== Skills and qualifications ==
== Skills and qualifications ==
Currently I am a second year Computer Engineering undergraduate student<br />
Currently, I am a final year Computer Engineering undergraduate student<br />
Languages: Ibo(native),English(native), French(Elementary)<br />
Languages: Ibo(native),English(native), French(Elementary)<br />
Programming skills: C/C++ ,Python, SQl,HTML/CSS,Java(elementary),php(elementary).
Programming skills: C/C++ ,Python, SQl,HTML/CSS,Java(elementary),php(elementary).


== None Summer-of-Code for the Summer ==
== None Summer-of-Code for the Summer ==
<p> As of now I have no other plans and I will make up to it in case If am having any change in my plans. I would be able to spend about 40+ hours a week and maybe even more. </p>
<p>I started working on this project for GSoC 2019 but was not selected to due to I did provide a link to pre contribution work and also I did not work on it for GSoC 2020 due to lack of time, I was busy with my academic work but am available to work on it this year for GSoC 2021. As of now, I have no other plans and I will make up for it in case If I am having any change in my plans. I would be able to spend about 40+ hours a week and maybe even more. </p>
----
----

[[Category:GSoC 2021 student proposals]]

Latest revision as of 15:41, 7 April 2021

GSOC 2021: Create a usable version of these language pair: English--Igbo

CONTACT INFORMATION[edit]

Name: Okonkwo Ifeanyichukwu

Location: Buea, Cameroon

University: University of Buea

E-mail: ifeanyijasper11@gmail.com

IRC: ifeanyi

Timezone: GMT +1

Github: https://github.com/Ifeanyijasper/

Why is it that you are interested in Apertium?[edit]

Apertium is a free and open-source translation machine and I have passion for machine learning and data science. I got to know about apertium through a friend who is a member of the organisation. Communication which is one of its kind is so welcoming i.e. everyone is willing to provide you a solution in case if you are stuck in a particular issue. I love Igbo language so much that am willing to get involve or participate in anything that concerns it.

Which of the published tasks are you interested in? What do you plan to do?[edit]

Apertium translation pair for English and Igbo[edit]

I am interested in adding a new language pair that is English-Igbo.

Why google should sponsor it?[edit]

Nigeria is a big country with a large population that attracts tourists and immigrants. On staying in the country 45% of people will tend to learn the native languages; of which Ibo is very popular among Nigeria's languages. Translating Apertium to ibo will go a long way, though indirectly to preserve Nigeria's rich culture. The language will be encouraged because tools like apertium will be available for people to use on the internet.

In the 21st-century apertium incorporating ibo as one of its languages will help in one way or the other to encourage other countries to easily interact with Igbo people. Most of the time whenever we travel anywhere in the world we meet at least one Nigerian and the communication would likely be in our Native language since it helps us feel we are in our homeland. In some rural areas in Nigeria, people speak only Igbo and if these places are visited by tourist they might need translation to English to communicate

Coding Challenge[edit]

1. Installed Apertium and necessary tools.

2. Add some words to bidix and ibo.lexc file.

3. Translated some words from this story as much as possible.

4. Push changes to the main git repository. eng-ibo and ibo

MILESTONES[edit]

Week 0: Community bonding

               Getting familiar with all the Apertium modules and it’s working. Discussion with mentors and clearing doubts. 
               Also, discussion with other selected members about their ideas in detail. Reading and gathering information about other
               different Machine translation tools.
               Reading and editing the wiki to include small changes for making it more easier for newbies to join Apertium.



First phase[edit]

Week 1:

               Improving Igbo monolingual dictionary
               Adding nouns,prepositions,adjectives to bilingual dictionary

Week 2:

          	Adding verbs,pronouns conjunctions to bilingual dictionary
                Write transfer rules for verbs and noun        	

Week 3:

          	Continue with the work.
                Adding verbs and more nouns from English Wiktionary

Week 4:

          	Update documentation
          	Preparing for evaluation.

Deliverable 1: Bilingual dictionary, basic transfer rules.



Second phase[edit]

Week 5:

          	Observing the sentence structure of both languages.
          	Fixing minor issues in Ibo dictionary.

Week 6:

          	Adding words to the bilingual dictionary.
               Adding words with tone markings.

Week 7:

               Continue adding words with tone markings.
          	Including transfer rules.

Week 8:

               Continue with the work.
               Test translation and prepare for evaluation.

Deliverable 2:Understandable translation between these two languages.



Third phase[edit]

Week 9:

                Extend bilingual dictionary.
          	Work on disambiguation rules. 

Week 10:

          	testvoc and improvements.
                More work on transfer rules.

Week 11:

          	Continue with the work. Testing using newspaper contents.

Week 12:

          	Writing documentation, complete testing and fixing bugs.


Final evaluation

Skills and qualifications[edit]

Currently, I am a final year Computer Engineering undergraduate student
Languages: Ibo(native),English(native), French(Elementary)
Programming skills: C/C++ ,Python, SQl,HTML/CSS,Java(elementary),php(elementary).

None Summer-of-Code for the Summer[edit]

I started working on this project for GSoC 2019 but was not selected to due to I did provide a link to pre contribution work and also I did not work on it for GSoC 2020 due to lack of time, I was busy with my academic work but am available to work on it this year for GSoC 2021. As of now, I have no other plans and I will make up for it in case If I am having any change in my plans. I would be able to spend about 40+ hours a week and maybe even more.