Difference between revisions of "Fijian/Transducer"

From LING073
Jump to: navigation, search
(→‎Notes)
 
(9 intermediate revisions by the same user not shown)
Line 2: Line 2:
 
The morphological transducer for Fijian is at:
 
The morphological transducer for Fijian is at:
 
https://github.swarthmore.edu/hwang11/ling073-fij
 
https://github.swarthmore.edu/hwang11/ling073-fij
 +
 +
Current Coverage: 51.08%
  
 
==Analyser Evaluation==
 
==Analyser Evaluation==
 
* Total number of stems in transducer: 21
 
* Total number of stems in transducer: 21
−
 
+
* Morph Test:
 +
:-Transitivity of Verbs: Passes 15, Total 15;
 +
:-Fist person inclusive pronouns: Passes 23, Total 23;
 +
:-First person exclusive pronouns: Passes 18, Total 18;
 +
:-Second person pronouns: Passes 21, Total 21;
 +
:-Third person pronouns: Passes 24, Total 24;
 
*Current Coverage: Running aq-covtest on my fij.corpus.basic.txt, I got:
 
*Current Coverage: Running aq-covtest on my fij.corpus.basic.txt, I got:
  
Line 107: Line 114:
 
===Final Evaluation===
 
===Final Evaluation===
 
*Number of passing and failing tests:
 
*Number of passing and failing tests:
−
*Number of twol rules added: 5
+
:-Transitivity of verbs: Passes 15, Total 15;
 +
:-First person inclusive pronouns: Passes 23, Total 23;
 +
:-First person exclusive pronouns: Passes 18, Total 18;
 +
:-Second person pronouns: Passes 19, Total 21;
 +
:-Third person pronouns: Passes 24, Total 24.
 +
*Number of twol rules added: 7
  
 
==Notes==
 
==Notes==
−
*I still have problems running morph tests. The "morph-test -csi fij.yaml | most" command always returns me with an error message saying that "The program 'most' is currently not installed. To run 'most' please ask your administrator to install the package 'most'," and some syntax errors in the morph-test file.
+
 
  
  

Latest revision as of 18:30, 22 March 2018

Transducer Link

The morphological transducer for Fijian is at: https://github.swarthmore.edu/hwang11/ling073-fij

Current Coverage: 51.08%

Analyser Evaluation

  • Total number of stems in transducer: 21
  • Morph Test:
-Transitivity of Verbs: Passes 15, Total 15;
-Fist person inclusive pronouns: Passes 23, Total 23;
-First person exclusive pronouns: Passes 18, Total 18;
-Second person pronouns: Passes 21, Total 21;
-Third person pronouns: Passes 24, Total 24;
  • Current Coverage: Running aq-covtest on my fij.corpus.basic.txt, I got:
-Number of tokenised words in the corpus: 1306
-Coverage: 4.67%
  • Initial top unknown words:

na 113

a 75

e 62

o 40

ni 40

mai 35

ka 33

i 30

sa 28

E 23

ko 19

vei 18

me 17

u 16

dua 13

kina 11

ki 10

Viti 10

koya 9

vaka 9

-The top unknown words na, a, and o are articles <art>: na and a are used with common nouns and o is used with pronouns and proper names.
-The unknown words me is a relator <rel>.
  • After adding the analyses of na, a, o, and me to my transducer, the coverage went from 4.67% to 24.35%.
-Current unknown words:

e 62

ni 40

mai 35

ka 33

i 30

sa 28

E 23

ko 19

vei 18

u 16

dua 13

kina 11

ki 10

Viti 10

koya 9

vaka 9

kena 8

levu 8

tu 8

vena 8

Generator Evaluation

Initial evaluation of morphological generation

  • Number of passed morphological analysis tests:
  • Current coverage: 24.35%

Final Evaluation

  • Number of passing and failing tests:
-Transitivity of verbs: Passes 15, Total 15;
-First person inclusive pronouns: Passes 23, Total 23;
-First person exclusive pronouns: Passes 18, Total 18;
-Second person pronouns: Passes 19, Total 21;
-Third person pronouns: Passes 24, Total 24.
  • Number of twol rules added: 7

Notes