Difference between revisions of "Waray/Transducer"

From LING073
Jump to: navigation, search
(Analyser Evaluation)
(Generator Evaluation)
 
(33 intermediate revisions by the same user not shown)
Line 2: Line 2:
 
* [https://github.swarthmore.edu/Ling073-sp21/ling073-war See Github repository]
 
* [https://github.swarthmore.edu/Ling073-sp21/ling073-war See Github repository]
  
==Analyser Evaluation==
+
===Analyser Evaluation===
 +
war.corpus
 +
{| class="wikitable" style="text-align: center
 +
|'''Date Evaluated'''
 +
|'''Coverage'''
 +
|'''Remaining unknown forms'''
 +
|-
 +
|''Sun 18 Apr 2021 04:10:45 AM EDT*''
 +
|''592 / 1259 (~0.47021445591739475774)''
 +
|''667''
 +
|-
 +
|Thu 22 Apr 2021 04:22:10 PM EDT
 +
|742 / 1239 (~0.59887005649717514124)
 +
|487
 +
|}
 +
''*Initial Evaluation''
  
 
====Lexical Information====
 
====Lexical Information====
* Lexicons: 15        
+
* Lexicons: 17        
* Lexicon entries: 112
+
* Lexicon entries: 120
 
* Patterns: 1
 
* Patterns: 1
* Pattern entries: 8
+
* Pattern entries: 9
  
 
====Counts for individual lexicon====
 
====Counts for individual lexicon====
NounRoot: 19
+
* NounRoot: 23
Determiners: 11
+
* Determiners: 13
PluralDet: 2
+
* PluralDet: 2
VerbPrefixes: 5
+
* VerbPrefixes: 5
VerbStems: 5
+
* VerbStems: 5
Pronouns: 31
+
* Pronouns: 31
Adverbs: 11
+
* ProperNouns: 1
Auxiliary: 1
+
* Adverbs: 11
All anonymous lexicons: 5
+
* Auxiliary: 1
 +
* Punctuaion: 22
 +
* All anonymous lexicons: 6
  
 
====Tests====
 
====Tests====
* <b>war.yaml</b>: Total passes: 56, Total fails: 15, Total: 71
+
As of Apr 22, 2021
 +
* '''war.yaml''': Total passes: 57, Total fails: 14, Total: 71
 +
* '''commonWords.yaml''': Total passes 4, Total fails: 16, Total: 20
  
==Notes==
+
====Current Unknown Words====
 +
TOP UNKNOWN WORDS:
 +
    15 ^nagkaada/*nagkaada$
 +
    12 ^hito/*hito$
 +
    11 ^uyon/*uyon$
 +
    11 ^linarang/*linarang$
 +
    10 ^may/*may$
 +
    10 ^langit/*langit$
 +
      9 ^klase/*klase$
 +
      9 ^hayop/*hayop$
 +
      8 ^katubigan/*katubigan$
 +
      7 ^tagsa/*tagsa$
 +
      7 ^ngatanan/*ngatanan$
 +
      7 ^kalamrag/*kalamrag$
 +
      7 ^basi/*basi$
 +
      6 ^nalupad/*nalupad$
 +
      6 ^liso/*liso$
 +
      6 ^iton/*iton$
 +
      6 ^haluag/*haluag$
 +
      6 ^espasyo/*espasyo$
 +
      6 ^bawbaw/*bawbaw$
 +
      6 ^aga/*aga$
 +
 
 +
===Notes===
 
* Tests for verbalized nouns not implemented yet
 
* Tests for verbalized nouns not implemented yet
* Disambiguation still needed
 
  
==Notes==
+
==Generator Evaluation==
 +
 
 +
====Analysis====
 +
<code>morph-test -csi tests/war.yaml</code>
  
 +
====Generation====
 +
<code>morph-test -cl tests/war.yaml</code>
  
==Generator Evaluation==
+
{| class="wikitable" style="text-align: center
 +
|'''Date Evaluated'''
 +
|'''Evaluation'''
 +
|'''Total passes'''
 +
|'''Total fails'''
 +
|'''Total'''
 +
|-
 +
|rowspan="2"|Apr 18, 2021*
 +
|''Analyser''
 +
|55
 +
|24
 +
|79
 +
|-
 +
|''Generator''
 +
|55
 +
|19
 +
|74
 +
|-
 +
|rowspan="2"|Apr 22, 2021
 +
|''Analyser''
 +
|57
 +
|14
 +
|71
 +
|-
 +
|''Generator''
 +
|56
 +
|18
 +
|74
 +
|}
 +
''*Initial Evaluation''
  
 +
* Currently, we have 4 rules in our twol file to handle verb conjugation.
  
[[Category: Sp21_Transducers]] [[Category: Waray]]
+
[[Category: Sp21_Transducers]] [[Category: Waray]]

Latest revision as of 18:18, 22 April 2021

Morphological Transducer

Analyser Evaluation

war.corpus

Date Evaluated Coverage Remaining unknown forms
Sun 18 Apr 2021 04:10:45 AM EDT* 592 / 1259 (~0.47021445591739475774) 667
Thu 22 Apr 2021 04:22:10 PM EDT 742 / 1239 (~0.59887005649717514124) 487

*Initial Evaluation

Lexical Information

  • Lexicons: 17
  • Lexicon entries: 120
  • Patterns: 1
  • Pattern entries: 9

Counts for individual lexicon

  • NounRoot: 23
  • Determiners: 13
  • PluralDet: 2
  • VerbPrefixes: 5
  • VerbStems: 5
  • Pronouns: 31
  • ProperNouns: 1
  • Adverbs: 11
  • Auxiliary: 1
  • Punctuaion: 22
  • All anonymous lexicons: 6

Tests

As of Apr 22, 2021

  • war.yaml: Total passes: 57, Total fails: 14, Total: 71
  • commonWords.yaml: Total passes 4, Total fails: 16, Total: 20

Current Unknown Words

TOP UNKNOWN WORDS:

    15 ^nagkaada/*nagkaada$
    12 ^hito/*hito$
    11 ^uyon/*uyon$
    11 ^linarang/*linarang$
    10 ^may/*may$
    10 ^langit/*langit$
     9 ^klase/*klase$
     9 ^hayop/*hayop$
     8 ^katubigan/*katubigan$
     7 ^tagsa/*tagsa$
     7 ^ngatanan/*ngatanan$
     7 ^kalamrag/*kalamrag$
     7 ^basi/*basi$
     6 ^nalupad/*nalupad$
     6 ^liso/*liso$
     6 ^iton/*iton$
     6 ^haluag/*haluag$
     6 ^espasyo/*espasyo$
     6 ^bawbaw/*bawbaw$
     6 ^aga/*aga$

Notes

  • Tests for verbalized nouns not implemented yet

Generator Evaluation

Analysis

morph-test -csi tests/war.yaml

Generation

morph-test -cl tests/war.yaml

Date Evaluated Evaluation Total passes Total fails Total
Apr 18, 2021* Analyser 55 24 79
Generator 55 19 74
Apr 22, 2021 Analyser 57 14 71
Generator 56 18 74

*Initial Evaluation

  • Currently, we have 4 rules in our twol file to handle verb conjugation.