Difference between revisions of "Japhug/Transducer"

Revision as of 22:08, 26 February 2023

This is the page for our Japhug transducer.

Evaluation

Total number of stems in transducer

Lexicons: 22
Lexicon entries: 99
Patterns: 10
Pattern entries: 22

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: 13
N-Collective: 1
Gender: 2
Numeral: 10
All anonymous lexicons: 8

Current coverage

Number of tokenised words in the corpus: 1238
Coverage: 24.23%

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

Top unknown words in the corpus:
85	 tɕe
68	 nɯ
41	 tɕendɤre
40	 kɯ
19	 ɕti
18	 toti
17	 ci
17	 ʑo
16	 βʑɯ
16	 pɣɤtɕɯ
16	 ɲɯŋu
15	 ma
14	 ri
14	 aʑo
13	 nɤkinɯ
13	 ra
12	 nɤki
12	 lɯlu
10	 nɤ
10	 ndɤre

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)