Difference between revisions of "Japhug/Transducer"

From LING073
Jump to: navigation, search
(→‎Notes)
Line 1: Line 1:
−
This is the transducer for Japhug.
+
This is the page for our [https://github.swarthmore.edu/Ling073-sp23/ling073-jya Japhug transducer].
−
 
 
−
[https://github.swarthmore.edu/Ling073-sp23/ling073-jya Our Code]  
 
  
  
Line 55: Line 53:
  
 
==Notes==
 
==Notes==
−
What tests still don't work and why:
+
Tests that completely fail: 
 +
 
 +
*analysis and generation (Irrelevant tests- they are the "house/houses" example by Jonathan)
  
−
*Reflexive-morph
+
*Reduplicated Collective-gen and morph (we avoided reduplication and sandhi for this lab)
  
−
*Passive-morph
+
*Gerund-gen and morph (gerund contains partial reduplication, so we didn't code it)
  
−
*Sigmatic Causative-gen and morph
+
*Sigmatic Causative-gen (0/11 test match gold)
  
−
*Reduplicated Collective-gen and morph
 
  
−
*Social Relation Collective-gen and morph
+
Tests that partially fail (We're able to generate all the gold standards in our terminal. Not sure why failing):
  
−
*Negation on Verbs-gen and morph
+
*Possessive prefixes on nouns-gen (2/25 test not passing) and morph (2/20 test not passing)
  
−
*Participles- morph (our gen pass the tests, and we're able to generate the words...)
+
*Negation on Verbs-gen (2/4 test do not match gold)  
  
−
*Possessive prefixes on nouns-morph (around 75% match gold...).
+
*Sigmatic Causative-morph (2/11 test match gold)  
  
−
Irrelevant tests that don't pass and can be ignored: analysis and generation (they are the "house/houses" example by Jonathan).
+
*Passive-morph (1/3 test not passing)  
 
    
 
    
  

Revision as of 21:39, 26 February 2023

This is the page for our Japhug transducer.


Evaluation

Total number of stems in transducer

Lexicons: 21

Lexicon entries: 96

Patterns: 9

Pattern entries: 21


Counts for individual lexicons:

Punctuation: 22

V-Negative: 2

N-Possessive: 12

V-Participles: 3

V-Stems: 21

V-Transitivity: 2

V-Causative: 1

V-Reflexive: 1

V-Passive: 1

N-Stems: 11

Gender: 2

N-Collective: 1

Numeral: 10

All anonymous lexicons: 7


Current coverage over your combined corpus:

The current list of top unknown words returned by aq-covtest

Number of tests that pass in each yaml file

Notes

Tests that completely fail:

  • analysis and generation (Irrelevant tests- they are the "house/houses" example by Jonathan)
  • Reduplicated Collective-gen and morph (we avoided reduplication and sandhi for this lab)
  • Gerund-gen and morph (gerund contains partial reduplication, so we didn't code it)
  • Sigmatic Causative-gen (0/11 test match gold)


Tests that partially fail (We're able to generate all the gold standards in our terminal. Not sure why failing):

  • Possessive prefixes on nouns-gen (2/25 test not passing) and morph (2/20 test not passing)
  • Negation on Verbs-gen (2/4 test do not match gold)
  • Sigmatic Causative-morph (2/11 test match gold)
  • Passive-morph (1/3 test not passing)