Difference between revisions of "Fijian/Transducer"

From LING073
Jump to: navigation, search
(→‎Analyser Evaluation)
(→‎Analyser Evaluation)
Line 4: Line 4:
  
 
==Analyser Evaluation==
 
==Analyser Evaluation==
−
Running aq-covtest on my fij.corpus.basic.txt, I got:
+
* Total number of stems in transducer: 21
  
−
Number of tokenised words in the corpus: 1306
+
*Current Coverage: Running aq-covtest on my fij.corpus.basic.txt, I got:
  
−
Coverage: 4.67%
+
:-Number of tokenised words in the corpus: 1306
 +
:-Coverage: 4.67%
  
−
Top unknown words:
+
*Top unknown words:
  
 
na 113
 
na 113

Revision as of 14:23, 1 March 2018

Transducer Link

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

Analyser Evaluation

  • Total number of stems in transducer: 21
  • Current Coverage: Running aq-covtest on my fij.corpus.basic.txt, I got:
-Number of tokenised words in the corpus: 1306
-Coverage: 4.67%
  • Top unknown words:

na 113

a 75

e 62

0 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

Generator Evaluation

Initial evaluation of morphological generation

Notes