Difference between revisions of "Judeo-Tat/Transducer"

From LING073
Jump to: navigation, search
(→‎Corpus)
(→‎Corpus)
Line 1: Line 1:
 
[https://github.swarthmore.edu/dyelsey1/ling073-jdt The code for a Morphological Transducer in Judeo-Tat can be found here.]
 
[https://github.swarthmore.edu/dyelsey1/ling073-jdt The code for a Morphological Transducer in Judeo-Tat can be found here.]
  
−
== Corpus ==
+
== Evaluation ==
−
For a corpus of 854 tokenised words, there is a coverage of 6.09%.
+
For a corpus of 854 tokenised words, there is a basic coverage of 6.09%.
  
 
*«by adding "{{morphTest|эри{{tag|post}}|эри}}" to the transducer, coverage went from 6.09% to 8.90%»
 
*«by adding "{{morphTest|эри{{tag|post}}|эри}}" to the transducer, coverage went from 6.09% to 8.90%»
Line 10: Line 10:
 
*«by adding "{{morphTest|хирс{{tag|n}}{{tag|sg}}|хирс}} (bear)" to the transducer, coverage went from 18.03% to 20.61%»
 
*«by adding "{{morphTest|хирс{{tag|n}}{{tag|sg}}|хирс}} (bear)" to the transducer, coverage went from 18.03% to 20.61%»
 
*«by adding "{{morphTest|мугу{{tag|vblex}}{{tag|sg}}{{tag|p1}}|мугу}} (bear)" to the transducer, coverage went from 20.61% to 21.66%»
 
*«by adding "{{morphTest|мугу{{tag|vblex}}{{tag|sg}}{{tag|p1}}|мугу}} (bear)" to the transducer, coverage went from 20.61% to 21.66%»
 +
===Current list of most common unknown words ===
 +
*кор
 +
*е
 +
*зугьун
 +
*пирэ
 +
*ве
 +
*гэндуьмэ
 +
*ми
 +
*Би
 +
*чугундурэ
 +
*в
 +
*Хьэйфи
 +
*Пирэ
 +
*гьер
 +
*корим
 +
*сохим
 +
*гуфдире
 +
*вэсал
 +
*нэ
 +
*тамбургъорэ
 +
*бахш
  
 
== Notes ==
 
== Notes ==

Revision as of 05:09, 15 February 2017

The code for a Morphological Transducer in Judeo-Tat can be found here.

Evaluation

For a corpus of 854 tokenised words, there is a basic coverage of 6.09%.

  • «by adding "эри<post> ↔ эри" to the transducer, coverage went from 6.09% to 8.90%»
  • «by adding "э<art> ↔ э" to the transducer, coverage went from 8.90% to 13.70%»
  • «by adding "эз<abl> ↔ эз" to the transducer, coverage went from 13.70% to 15.57%»
  • «by adding "мэрд<n><sg> ↔ мэрд (man)" to the transducer, coverage went from 15.57% to 18.03%»
  • «by adding "хирс<n><sg> ↔ хирс (bear)" to the transducer, coverage went from 18.03% to 20.61%»
  • «by adding "мугу<vblex><sg><p1> ↔ мугу (bear)" to the transducer, coverage went from 20.61% to 21.66%»

Current list of most common unknown words

  • кор
  • е
  • зугьун
  • пирэ
  • ве
  • гэндуьмэ
  • ми
  • Би
  • чугундурэ
  • в
  • Хьэйфи
  • Пирэ
  • гьер
  • корим
  • сохим
  • гуфдире
  • вэсал
  • нэ
  • тамбургъорэ
  • бахш

Notes

There are currently 3 sets of tests that are not working for a total of 9 failed tests.

Compound words

I couldn't get compounds to work. It was difficult using the unfamiliar syntax to do anything more complicated than suffixes.

Prefixes

Prefixes are also difficult due to the unfamiliar syntax.

Multiple words

The final failed tests were those that involved multiple words. I was unable to create a transducer than successfully compiled.