Difference between revisions of "Nuosu/Transducer"

From LING073
Jump to: navigation, search
(Evaluation)
(Evaluation)
 
Line 1: Line 1:
 
Here is the Git Repo for the [https://github.swarthmore.edu/Ling073-sp22/ling073-iii Nuosu transducer].
 
Here is the Git Repo for the [https://github.swarthmore.edu/Ling073-sp22/ling073-iii Nuosu transducer].
  
== Evaluation ==
+
= Evaluation =
  
=== Feb 25, 2022 ===
+
== Feb 25, 2022 ==
  
==== Corpus Coverage ====
+
=== Corpus Coverage ===
  
 
Our current coverage over the bible is 46%.
 
Our current coverage over the bible is 46%.
Line 34: Line 34:
 
nuosu.bible Fri 25 Feb 2022 07:40:27 PM EST 16156/35466 ~0.45553487847515930751
 
nuosu.bible Fri 25 Feb 2022 07:40:27 PM EST 16156/35466 ~0.45553487847515930751
  
=== Apr 30, 2022 ===
+
== Apr 30, 2022 ==
  
==== Stem Information ====
+
=== Stem Information ===
  
 
'''Lexical Information'''
 
'''Lexical Information'''
Line 91: Line 91:
 
All anonymous lexicons: 23
 
All anonymous lexicons: 23
  
==== Corpus Coverage ====
+
=== Corpus Coverage ===
  
 
Our current coverage over the bible is 75%.
 
Our current coverage over the bible is 75%.

Latest revision as of 09:48, 30 April 2022

Here is the Git Repo for the Nuosu transducer.

Evaluation

Feb 25, 2022

Corpus Coverage

Our current coverage over the bible is 46%.

TOP UNKNOWN WORDS:

  1021 ^ꄷ。/*ꄷ。$
   268 ^ꀕ/*ꀕ$
   154 ^、/*、$
   139 ^ꄷ/*ꄷ$
   131 ^ꎔ/*ꎔ$
   111 ^ꃅ/*ꃅ$
    60 ^ꄷꅲ。/*ꄷꅲ。$
    53 ^ꑳꌠꆏ:/*ꑳꌠꆏ:$
    42 ^ꉢꇯꍝꃅ/*ꉢꇯꍝꃅ$
    39 ^ꏢ/*ꏢ$
    36 ^ꏀ/*ꏀ$
    34 ^ꌃ/*ꌃ$
    33 ^ꉢ/*ꉢ$
    31 ^ꂟ。/*ꂟ。$
    28 ^꒰/*꒰$
    28 ^ꌠ/*ꌠ$
    26 ^ꌠꉬ。/*ꌠꉬ。$
    22 ^ꀋ/*ꀋ$
    22  ^ꏢ/*ꏢ$
    21 ^ꅇ/*ꅇ$

coverage: 16156 / 35466 (~0.45553487847515930751) remaining unknown forms: 19310 nuosu.bible Fri 25 Feb 2022 07:40:27 PM EST 16156/35466 ~0.45553487847515930751

Apr 30, 2022

Stem Information

Lexical Information

Lexicons: 44

Lexicon entries: 276

Patterns: 2

Pattern entries: 25

Counts for individual lexicons

AdjStems: 15

SizePrefixes: 3

NegPrefixes: 1

VerbStems: 52

NmlzSuffixes: 5

AdjzSuffixes: 2

Intensification: 1

NounStems: 39

Pronouns: 20

QuoteStems: 1

Preposition: 18

Postposition: 8

Classifier: 19

Particles: 10

Determiner: 1

Conjunction: 2

Adverb: 7

Punctuation: 29

Numeral: 10

Numbers: 10 All anonymous lexicons: 23

Corpus Coverage

Our current coverage over the bible is 75%.

TOP UNKNOWN WORDS:

  1432 ^ꌋ/*ꌋ$
   640 ^ꂶ/*ꂶ$
   617 ^ꅇ/*ꅇ$
   581 ^ꎔ/*ꎔ$
   578 ^ꑲ/*ꑲ$
   572 ^ꈨ/*ꈨ$
   540 ^ꀉ/*ꀉ$
   502 ^ꀋ/*ꀋ$
   476 ^ꀋꄸ/*ꀋꄸ$
   411 ^ꀋꎪ/*ꀋꎪ$
   394 ^ꈍ/*ꈍ$
   388 ^ꇫ/*ꇫ$
   386 ^ꀕ/*ꀕ$
   366 ^ꐥ/*ꐥ$
   339 ^ꌦ/*ꌦ$
   335 ^ꅐ/*ꅐ$
   311 ^ꊌ/*ꊌ$
   310 ^ꃀ/*ꃀ$
   291 ^ꈀ/*ꈀ$
   291 ^ꅍ/*ꅍ$

coverage: 182179 / 243953 (~0.74677909269408451628) remaining unknown forms: 61774 iii.bible2 Sat 30 Apr 2022 09:42:02 AM EDT 182179/243953 ~0.74677909269408451628