Difference between revisions of "User:GD/proposal"

From Apertium
Jump to navigation Jump to search
Line 41: Line 41:
 
<p> 4. Latin and Russian packages </p>
 
<p> 4. Latin and Russian packages </p>
 
<p> 5. Created a folder for a Lat-Rus project </p>
 
<p> 5. Created a folder for a Lat-Rus project </p>
<p> 6. Dictionary work comments : </p>
+
<p> 6. '''Dictionary work comments : '''</p>
 
Existent dictionaries are good, especially this Russian one, but Latin is not complet at all. There is much work to do.
 
Existent dictionaries are good, especially this Russian one, but Latin is not complet at all. There is much work to do.
 
<p>- Noun declension system isn't complete.</p>
 
<p>- Noun declension system isn't complete.</p>
Line 49: Line 49:
 
<p>- Furthermore, there are some other types (verba deponentia et semideponentia etc) with non-standard paradigm. </p>
 
<p>- Furthermore, there are some other types (verba deponentia et semideponentia etc) with non-standard paradigm. </p>
 
<p>- There are almost no irregular verbs (they are the most popular ones: 'can/be able', 'to carry', 'to want', 'to prefer', 'not to want', 'to happen') except for 'to be' and 'to go'.</p>
 
<p>- There are almost no irregular verbs (they are the most popular ones: 'can/be able', 'to carry', 'to want', 'to prefer', 'not to want', 'to happen') except for 'to be' and 'to go'.</p>
<p> 7. Added some words from Mary and James story that fit existent paradigms </p>
+
<p> 7. '''Added some words''' from Mary and James story that fit existent paradigms </p>
 
<p> 8. Extended acx file to process long vowel forms and to keep in mind U|V and J|I unity in non-standardized texts </p>
 
<p> 8. Extended acx file to process long vowel forms and to keep in mind U|V and J|I unity in non-standardized texts </p>
 
<p> 9. Compiled automorf and autogen files, tried using echo with pre-existing and added words. It works. </p>
 
<p> 9. Compiled automorf and autogen files, tried using echo with pre-existing and added words. It works. </p>
 
<p> 10. If we process Mary and James story wit latin automorf, we will see that are lots of common words are not in the dictionary (it confirms first impression after looking through the dictionary). Russian aumorf is good and can process this sample story. </p>
 
<p> 10. If we process Mary and James story wit latin automorf, we will see that are lots of common words are not in the dictionary (it confirms first impression after looking through the dictionary). Russian aumorf is good and can process this sample story. </p>
  +
<p> 11. '''Done some transfer rules and translated 2 sentences.''' </p>
 
<p>'''Now I'm working on other sentences'''</p>
   
  +
<p> '''My project on Github: ''' https://github.com/glaz-dikobraz/GSoC_Lat-Rus </p>
<p>'''Now I'm working on bidix and transfer rules.'''</p>
 
 
   
   

Revision as of 20:27, 1 April 2017

Contact information

Name: Irina Glazunova

Location: Moscow, Russia

University: NRU HSE, Moscow (National Research University Higher School of Economics)

E-mail: glaz.dikobraz@gmail.com

IRC: G_D

Timezone: UTC+3

Am I good enough?

Education: Bachelor's Degree in Fundamental and Computational Linguistics (2015-2019) at NRU HSE

Courses:

  • Programming (Python, Flask, HTML)
  • Morphology, Syntax, Semantics, Typology/Language Diversity
  • Mathematics (Discrete Mathemathics, Linear Algebra and Calculus, Probability Theory, Mathematical Statistics, Computability and Complexity)
  • Latin, Latin in modern Linguistics, Ancient Literature

Languages: Russian (native), English (Academic), French, Latin

Personal qualities: responsibility, punctuality, being hard-working, passion for Latin and programming, perseverance, resistance to stress

Why is it I am interested in machine translation? Why is it that I am interested in Apertium?

The speed of information circulation does not allow to spend time on human translation. I am truly interested in formal methods and models because they represent the way any language is constructed (as I see them). Despite some exceptions, in general language is very logical and the main problem is how to find proper systematic description. Apertium is a powerful platform that allows to build impressive rule-based engines. Languages like Latin are well-ordered, particularly their morphology, so it makes rule-based translation very promising.

Which of the published tasks am I interested in? What do I plan to do?

I would like to add Latin-Russian language pair. I plan to do my best to reach high results, more details are given in Proposal part.

Proposal

Latin-Russian language pair

Why Google and Apertium should sponsor it? How and who it will benefit in society?

Latin is the language of a great importance. Furthermore, studying Latin has a centuries-old history in Russia. Besides, Russian is spoken in different countries so much larger audience will benefit from this project. In Russia there are a lot of universities where students study Latin (faculties of Linguistics, Philology, History, Law, Medicine). Consequently, there is need for translation, not to mention a great heritage of ancient writers, poets and philosophers as Cicero, Catullus and others. Today only a couple of platforms have Latin-Russian pair, but they still have a lot work to do. So, a perspective of creating this pair is very promising. What is more, it is promising because these languages have a lot in common (morphological system, syntactic role marking).

Coding Challenge

I'm working on it now

This section contains some information that clarifies laconic points in further workplan

Current success :

1. VirtualBox

2. Apertium VirtualBox

3. Core tools

4. Latin and Russian packages

5. Created a folder for a Lat-Rus project

6. Dictionary work comments :

Existent dictionaries are good, especially this Russian one, but Latin is not complet at all. There is much work to do.

- Noun declension system isn't complete.

- There is no declention pattern for comparative and superlative adjectives. There should be a distinction between adjectives that have these form and those that do not have them.

- At this moment I do not agree with "long vowels" in noun paradigms. I think if they are given in input, they can be processed with acx similarity rules. It is a bit strange because there are no long vowels in verb paradigm.

- There is only one type of verb paradigm - the first one for verbs with -are infinitives like amo|amare ('to love'). But there are a lot of other verbs from II, III (a,b) and IV types.

- Furthermore, there are some other types (verba deponentia et semideponentia etc) with non-standard paradigm.

- There are almost no irregular verbs (they are the most popular ones: 'can/be able', 'to carry', 'to want', 'to prefer', 'not to want', 'to happen') except for 'to be' and 'to go'.

7. Added some words from Mary and James story that fit existent paradigms

8. Extended acx file to process long vowel forms and to keep in mind U|V and J|I unity in non-standardized texts

9. Compiled automorf and autogen files, tried using echo with pre-existing and added words. It works.

10. If we process Mary and James story wit latin automorf, we will see that are lots of common words are not in the dictionary (it confirms first impression after looking through the dictionary). Russian aumorf is good and can process this sample story.

11. Done some transfer rules and translated 2 sentences.

Now I'm working on other sentences

My project on Github: https://github.com/glaz-dikobraz/GSoC_Lat-Rus


Week by week work plan

Week 0: until 05/29 : Preparation

          	Get familiar with Apertium system in details (wiki-sources, installing, creating files etc)
          	Get a corpora of texts for future test and frequency list by using both Wikipedia and 
                   Latin and classic texts by Caesar, Cicero, Vergilius and others.
          	Plan every step and write down everything as formally as it is possible (in natural language)
          	Discuss details with a mentor
          	U\V and I\J problem

First phase

Week 1: 05\30 – 06\05 : Dictionary: nouns & adjectives (they have same declension patterns)

          	Add nouns to dictionary (monodix and bidix)
          	Describe morphology
          	Add prepositions (they are closely related to nouns)

Week 2: 06\07 – 06\12 : Dictionary: verbs

          	Add verbs to dictionary (monodix and bidix)
          	Plan how to convert basic times

Week 3: 06\13 – 06\19 : Transfer rules Start writing transfer rules

          	Write basic transfer rules related to morphological transfers
          	Similar cases (case systems of these languages have a lot in common)

Week 4: 06\20 – 06\26 :

          	Extend dictionary
          	Add word from other classes to the dictionary (especially, closed classes)
          	Finish all work scheduled for this period
          	Prepare for the first evaluation
          	Prepare detailed theoretical basis for the next phase

Comment: first part is meant to be mostly technical and consist of some general and routine work.

Results: dictionary data, basic rules, morphological system, first testing

Second phase

Week 5: 06\27 – 07\03 : Syntactic rules (word order)

          	Solve general word order problems

Week 6: 07\04 – 07\10 : Structures

          	Add basic structures as accusativus cum infinitivo, ablativus absolutus etc

Week 7: 07\11 – 07\17 : Extend dictionary

          	Add more words from open classes (monodix and bidix)

Week 8: 07\18 – 07\24 : Context based disambiguation

Comment: second part is meant to be main part that suppose working on translation algorithms.

Results: extended dictionary data, syntactic rules, beta version of the system is ready to be used, beta testing

Third phase

Week 9: 07\25 – 07\31 : Syntactic rules 2

          	Extend number of syntactic rules
          	Testing

Week 10: 08\01 – 08\07 : Testing

          	Fixing issues that would appear
          	Extending data or rules (depending on previous results)

Week 11: 08\08 – 08\14 : Vacation

          	I will be able to do some work, I will have a laptop but may have some troubles with internet access.

Week 12: 08\15 – 08\21 : Final work on details

          	Put everything in order

Comment: improving system as much as it possible

Results: all rules written, final version of the system, testing, bugs fixed


Final evaluation

Non-Summer-of-Code plans you have for the Summer

GSoC is the only project I have this summer. I have a couple of exams on Week 4 so I planned a task that would be possible at that time and I planned vacation on Week 11 and scheduled more work in July and the beginning of August when I will be able to work more.