Difference between revisions of "Amis/Transducer"
(→Final evaluation of morphological generation: updated after adding spelrelax and fixing locative gold) |
|||
| Line 73: | Line 73: | ||
Instrumental Applicative: 6/6 tests match gold | Instrumental Applicative: 6/6 tests match gold | ||
| − | Locative Applicative: | + | Locative Applicative: 6/6 match gold |
Factual Mood: 5/5 match gold | Factual Mood: 5/5 match gold | ||
| Line 84: | Line 84: | ||
TOP UNKNOWN WORDS: | TOP UNKNOWN WORDS: | ||
| − | + | 115 ^ko/*ko$ | |
95 ^i/*i$ | 95 ^i/*i$ | ||
58 ^to/*to$ | 58 ^to/*to$ | ||
55 ^no/*no$ | 55 ^no/*no$ | ||
| − | |||
43 ^o/*o$ | 43 ^o/*o$ | ||
34 ^tamdaw/*tamdaw$ | 34 ^tamdaw/*tamdaw$ | ||
| − | |||
| − | |||
24 ^Tapang/*Tapang$ | 24 ^Tapang/*Tapang$ | ||
23 ^takowanan/*takowanan$ | 23 ^takowanan/*takowanan$ | ||
| Line 99: | Line 96: | ||
16 ^tatiihay/*tatiihay$ | 16 ^tatiihay/*tatiihay$ | ||
14 ^Tisowanan/*Tisowanan$ | 14 ^Tisowanan/*Tisowanan$ | ||
| − | |||
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: | + | 10 ^mo/*mo$ |
| − | remaining unknown forms: | + | 10 ^ka/*ka$ |
| − | ambiguity: | + | 10 ^faloco/*faloco$ |
| − | ami.corpus Thu Mar 2 | + | 10 ^dmak/*dmak$ |
| − | + | coverage: 759 / 2107 (~0.36022781205505457997) | |
| + | remaining unknown forms: 1348 | ||
| + | ambiguity: 2366 / 2107 (~1.12292358803986710963) | ||
| + | ami.corpus Thu Mar 2 09:03:45 PM EST 2023 759/2107 ~0.36022781205505457997 \| 2366/2107 ~1.12292358803986710963 | ||
[[Category:Amis]] [[Category:Sp23_Transducers]] | [[Category:Amis]] [[Category:Sp23_Transducers]] | ||
Revision as of 02:07, 3 March 2023
Contents
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$
46 ^ako/*ako$
43 ^o/*o$
34 ^tamdaw/*tamdaw$
33 ^Iso/*Iso$
31 ^kako/*kako$
24 ^Tapang/*Tapang$
23 ^takowanan/*takowanan$
17 ^ato/*ato$
17 ^Tapangaw/*Tapangaw$
16 ^tatiihay/*tatiihay$
14 ^Tisowanan/*Tisowanan$
14 ^Kiso/*Kiso$
13 ^O/*O$
12 ^cangra/*cangra$
12 ^ada/*ada$
12 ^Kawas/*Kawas$
coverage: 574 / 2107 (~0.27242524916943521595) remaining unknown forms: 1533 ambiguity: 2277 / 2107 (~1.08068343616516373991)
Corpus 1 of 4: Instrumental Applicative-morph
6/6 (100.0%) tests pass (2/6 (33.33%) match gold)
Corpus 2 of 4: Locative Applicative-morph
6/6 (100.0%) tests pass (0/6 (0.0%) match gold)
Corpus 3 of 4: Factual Mood-morph
5/5 (100.0%) tests pass (3/5 (60.0%) match gold)
Corpus 4 of 4: Pronouns-morph
24/24 (100.0%) tests pass (7/24 (29.17%) 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%.
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
Instrumental Applicative: 6/6 tests match gold
Locative Applicative: 6/6 match gold
Factual Mood: 5/5 match gold
Pronouns: 11/24 match gold
Number Plural Marker: 1/3 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$
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 09:03:45 PM EST 2023 759/2107 ~0.36022781205505457997 \| 2366/2107 ~1.12292358803986710963
