Difference between revisions of "Amis/Transducer"

From LING073
Jump to: navigation, search
(Undo revision 20287 by Mchalfo1 (talk))
 
(5 intermediate revisions by 2 users not shown)
Line 9: Line 9:
 
     58 ^to/*to$
 
     58 ^to/*to$
 
     55 ^no/*no$
 
     55 ^no/*no$
−
    46 ^ako/*ako$
 
 
     43 ^o/*o$
 
     43 ^o/*o$
 
     34 ^tamdaw/*tamdaw$
 
     34 ^tamdaw/*tamdaw$
−
    33 ^Iso/*Iso$
 
−
    31 ^kako/*kako$
 
 
     24 ^Tapang/*Tapang$
 
     24 ^Tapang/*Tapang$
 
     23 ^takowanan/*takowanan$
 
     23 ^takowanan/*takowanan$
Line 20: Line 17:
 
     16 ^tatiihay/*tatiihay$
 
     16 ^tatiihay/*tatiihay$
 
     14 ^Tisowanan/*Tisowanan$
 
     14 ^Tisowanan/*Tisowanan$
−
    14 ^Kiso/*Kiso$
 
 
     13 ^O/*O$
 
     13 ^O/*O$
−
    12 ^cangra/*cangra$
 
 
     12 ^ada/*ada$
 
     12 ^ada/*ada$
 
     12 ^Kawas/*Kawas$
 
     12 ^Kawas/*Kawas$
−
coverage: 574 / 2107 (~0.27242524916943521595)
+
    11 ^ma/*ma$
−
remaining unknown forms: 1533
+
    10 ^mo/*mo$
−
ambiguity: 2277 / 2107 (~1.08068343616516373991)
+
    10 ^ka/*ka$
 +
    10 ^faloco/*faloco$
 +
    10 ^dmak/*dmak$
 +
coverage: 759 / 2107 (~0.36022781205505457997)
 +
remaining unknown forms: 1348
 +
ambiguity: 2366 / 2107 (~1.12292358803986710963)
 +
ami.corpus Thu Mar 2 09:39:48 PM EST 2023 759/2107 ~0.36022781205505457997 \| 2366/2107 ~1.12292358803986710963
 +
 
 +
Corpus 1 of 5: Instrumental Applicative-morph
 +
  6/6 (100.0%) tests pass (6/6 (100.0%) match gold)
  
−
Corpus 1 of 4: Instrumental Applicative-morph
+
Corpus 2 of 5: Locative Applicative-morph
−
   6/6 (100.0%) tests pass (2/6 (33.33%) match gold)
+
   6/6 (100.0%) tests pass (6/6 (100.0%) match gold)
  
−
Corpus 2 of 4: Locative Applicative-morph
+
Corpus 3 of 5: Factual Mood-morph
−
   6/6 (100.0%) tests pass (0/6 (0.0%) match gold)
+
   5/5 (100.0%) tests pass (5/5 (100.0%) match gold)
  
−
Corpus 3 of 4: Factual Mood-morph
+
Corpus 4 of 5: Pronouns-morph
−
   5/5 (100.0%) tests pass (3/5 (60.0%) match gold)
+
   24/24 (100.0%) tests pass (11/24 (45.83%) match gold)
  
−
Corpus 4 of 4: Pronouns-morph
+
Corpus 5 of 5: Number Plural Marker-morph
−
   24/24 (100.0%) tests pass (7/24 (29.17%) match gold)
+
   3/3 (100.0%) tests pass (2/3 (66.67%) match gold)
  
 
All tests pass.
 
All tests pass.
Line 46: Line 50:
  
 
After adding the most uncommon word a<conj> to the transducer, coverage went from 19.93% to 27.25%.
 
After adding the most uncommon word a<conj> to the transducer, coverage went from 19.93% to 27.25%.
 +
After accomodating for o/u alternation, coverage went from 27.25% to 36.02%.
  
 
==Generator Evaluation==
 
==Generator Evaluation==
Line 71: Line 76:
  
 
===Final evaluation of morphological generation===
 
===Final evaluation of morphological generation===
−
Instrumental Applicative: 6/6 tests match gold
+
Corpus 1 of 8: Instrumental Applicative-gen
 +
  6/6 (100.0%) tests pass (5/6 (83.33%) match gold)
  
−
Locative Applicative: 0/6 match gold
+
Corpus 2 of 8: Locative Applicative-gen
 +
  6/6 (100.0%) tests pass (2/6 (33.33%) match gold)
  
−
Factual Mood: 5/5 match gold
+
Corpus 3 of 8: Factual Mood-gen
 +
  5/5 (100.0%) tests pass (4/5 (80.0%) match gold)
  
−
Pronouns: 11/24 match gold
+
Corpus 4 of 8: Pronouns-gen
 +
  28/28 (100.0%) tests pass (19/28 (67.86%) match gold)
 +
 
 +
Corpus 5 of 8: Number Plural Marker-gen
 +
  4/4 (100.0%) tests pass (2/4 (50.0%) match gold)
 +
 
 +
Corpus 6 of 8: Regular Verbs-gen
 +
  12/12 (100.0%) tests pass (5/12 (41.67%) match gold)
 +
 
 +
Corpus 7 of 8: Optative Mood-gen
 +
  5/5 (100.0%) tests pass (5/5 (100.0%) match gold)
 +
 
 +
Corpus 8 of 8: Spellrelax-gen
 +
  6/6 (100.0%) tests pass (0/6 (0.0%) match gold)
  
−
Number Plural Marker: 1/3 match gold
 
  
 
We added 5 twol rules.  
 
We added 5 twol rules.  
Line 88: Line 108:
 
     58 ^to/*to$
 
     58 ^to/*to$
 
     55 ^no/*no$
 
     55 ^no/*no$
−
    46 ^ako/*ako$
 
 
     43 ^o/*o$
 
     43 ^o/*o$
 
     34 ^tamdaw/*tamdaw$
 
     34 ^tamdaw/*tamdaw$
−
    33 ^Iso/*Iso$
 
−
    31 ^kako/*kako$
 
−
    24 ^Tapang/*Tapang$
 
 
     23 ^takowanan/*takowanan$
 
     23 ^takowanan/*takowanan$
 
     17 ^ato/*ato$
 
     17 ^ato/*ato$
−
    17 ^Tapangaw/*Tapangaw$
 
 
     16 ^tatiihay/*tatiihay$
 
     16 ^tatiihay/*tatiihay$
 
     14 ^Tisowanan/*Tisowanan$
 
     14 ^Tisowanan/*Tisowanan$
−
    14 ^Kiso/*Kiso$
 
 
     13 ^O/*O$
 
     13 ^O/*O$
 
     12 ^ada/*ada$
 
     12 ^ada/*ada$
 
     12 ^Kawas/*Kawas$
 
     12 ^Kawas/*Kawas$
 
     11 ^ma/*ma$
 
     11 ^ma/*ma$
−
coverage: 601 / 2107 (~0.28523967726625533935)
+
    10 ^mo/*mo$
−
remaining unknown forms: 1506
+
    10 ^ka/*ka$
−
ambiguity: 2277 / 2107 (~1.08068343616516373991)
+
    10 ^faloco/*faloco$
−
ami.corpus Thu Mar 2 08:13:00 PM EST 2023 601/2107 ~0.28523967726625533935 \| 2277/2107 ~1.08068343616516373991
+
    10 ^dmak/*dmak$
 +
    10 ^an/*an$
 +
      9 ^sowal/*sowal$
 +
coverage: 806 / 2107 (~0.38253440911248220218)
 +
remaining unknown forms: 1301
 +
ambiguity: 2366 / 2107 (~1.12292358803986710963)
 +
ami.corpus Tue Mar 14 10:48:24 AM EDT 2023 806/2107 ~0.38253440911248220218 \| 2366/2107 ~1.12292358803986710963
  
  
  
 
[[Category:Amis]] [[Category:Sp23_Transducers]]
 
[[Category:Amis]] [[Category:Sp23_Transducers]]

Latest revision as of 14:48, 14 March 2023

Evaluation

Code: https://github.swarthmore.edu/Ling073-sp23/ling073-ami

There are 75 stems in the transducer.

TOP UNKNOWN WORDS: 

   115 ^ko/*ko$
    95 ^i/*i$
    58 ^to/*to$
    55 ^no/*no$
    43 ^o/*o$
    34 ^tamdaw/*tamdaw$
    24 ^Tapang/*Tapang$
    23 ^takowanan/*takowanan$
    17 ^ato/*ato$
    17 ^Tapangaw/*Tapangaw$
    16 ^tatiihay/*tatiihay$
    14 ^Tisowanan/*Tisowanan$
    13 ^O/*O$
    12 ^ada/*ada$
    12 ^Kawas/*Kawas$
    11 ^ma/*ma$
    10 ^mo/*mo$
    10 ^ka/*ka$
    10 ^faloco/*faloco$
    10 ^dmak/*dmak$

coverage: 759 / 2107 (~0.36022781205505457997) remaining unknown forms: 1348 ambiguity: 2366 / 2107 (~1.12292358803986710963) ami.corpus Thu Mar 2 09:39:48 PM EST 2023 759/2107 ~0.36022781205505457997 \| 2366/2107 ~1.12292358803986710963

Corpus 1 of 5: Instrumental Applicative-morph 

 6/6 (100.0%) tests pass (6/6 (100.0%) match gold)

Corpus 2 of 5: Locative Applicative-morph 

 6/6 (100.0%) tests pass (6/6 (100.0%) match gold)

Corpus 3 of 5: Factual Mood-morph 

 5/5 (100.0%) tests pass (5/5 (100.0%) match gold)

Corpus 4 of 5: Pronouns-morph 

 24/24 (100.0%) tests pass (11/24 (45.83%) match gold)

Corpus 5 of 5: Number Plural Marker-morph 

 3/3 (100.0%) tests pass (2/3 (66.67%) match gold)

All tests pass.

Notes

After adding the most uncommon word a<conj> to the transducer, coverage went from 19.93% to 27.25%. After accomodating for o/u alternation, coverage went from 27.25% to 36.02%.

Generator Evaluation

Initial evaluation of morphological generation

number of passing and failing morphological analysis tests at this point:

Corpus 1 of 5: Instrumental Applicative-gen 

 6/6 (100.0%) tests pass (0/6 (0.0%) match gold)

Corpus 2 of 5: Locative Applicative-gen 

 6/6 (100.0%) tests pass (0/6 (0.0%) match gold)

Corpus 3 of 5: Factual Mood-gen 

 5/5 (100.0%) tests pass (3/5 (60.0%) match gold)

Corpus 4 of 5: Pronouns-gen 

 28/28 (100.0%) tests pass (3/28 (10.71%) match gold)

Corpus 5 of 5: Number Plural Marker-gen 

 1/1 (100.0%) tests pass (0/1 (0.0%) match gold)

All tests pass.

Coverage: 26.22%

Final evaluation of morphological generation

Corpus 1 of 8: Instrumental Applicative-gen 

 6/6 (100.0%) tests pass (5/6 (83.33%) match gold)

Corpus 2 of 8: Locative Applicative-gen 

 6/6 (100.0%) tests pass (2/6 (33.33%) match gold)

Corpus 3 of 8: Factual Mood-gen 

 5/5 (100.0%) tests pass (4/5 (80.0%) match gold)

Corpus 4 of 8: Pronouns-gen 

 28/28 (100.0%) tests pass (19/28 (67.86%) match gold)

Corpus 5 of 8: Number Plural Marker-gen 

 4/4 (100.0%) tests pass (2/4 (50.0%) match gold)

Corpus 6 of 8: Regular Verbs-gen 

 12/12 (100.0%) tests pass (5/12 (41.67%) match gold)

Corpus 7 of 8: Optative Mood-gen 

 5/5 (100.0%) tests pass (5/5 (100.0%) match gold)

Corpus 8 of 8: Spellrelax-gen 

 6/6 (100.0%) tests pass (0/6 (0.0%) match gold)


We added 5 twol rules.

TOP UNKNOWN WORDS: 

   115 ^ko/*ko$
    95 ^i/*i$
    58 ^to/*to$
    55 ^no/*no$
    43 ^o/*o$
    34 ^tamdaw/*tamdaw$
    23 ^takowanan/*takowanan$
    17 ^ato/*ato$
    16 ^tatiihay/*tatiihay$
    14 ^Tisowanan/*Tisowanan$
    13 ^O/*O$
    12 ^ada/*ada$
    12 ^Kawas/*Kawas$
    11 ^ma/*ma$
    10 ^mo/*mo$
    10 ^ka/*ka$
    10 ^faloco/*faloco$
    10 ^dmak/*dmak$
    10 ^an/*an$
     9 ^sowal/*sowal$

coverage: 806 / 2107 (~0.38253440911248220218) remaining unknown forms: 1301 ambiguity: 2366 / 2107 (~1.12292358803986710963) ami.corpus Tue Mar 14 10:48:24 AM EDT 2023 806/2107 ~0.38253440911248220218 \| 2366/2107 ~1.12292358803986710963

Retrieved from "http://wikis.swarthmore.edu/ling073/index.php?title=Amis/Transducer&oldid=20397"