Difference between revisions of "Guarani/Transducer"

From LING073
Jump to: navigation, search
(→‎Evaluation)
Line 2: Line 2:
 
=Evaluation=
 
=Evaluation=
 
The current corpus coverage is 2.85% (out of 1016 tokenized words in the corpus).
 
The current corpus coverage is 2.85% (out of 1016 tokenized words in the corpus).
 +
 +
The most missed words were:
 +
 +
{| class="wikitable"
 +
|+Class tags
 +
!'''Word'''
 +
!'''Occurences'''
 +
|-
 +
|''ha''
 +
|44
 +
|-
 +
|''a''
 +
|43
 +
|-
 +
|''va''
 +
|41
 +
|-
 +
|''pe''
 +
|27
 +
|-
 +
|''i''
 +
|-
 +
|''e''
 +
|25
 +
|-
 +
|''e''
 +
|20
 +
|-
 +
|''m''
 +
|18
 +
|-
 +
|''ra''
 +
|17
 +
|-
 +
|''ta''
 +
|10
 +
|-
 +
|''o''
 +
|10
 +
|-
 +
|''guarani''
 +
|9
 +
|-
 +
|''up''
 +
|9
 +
|-
 +
|''ñe''
 +
|9
 +
|-
 +
|''yvy''
 +
|9
 +
|-
 +
|''y''
 +
|9
 +
|-
 +
|''icha''
 +
|9
 +
|-
 +
|''me''
 +
|8
 +
|-
 +
|''rã''
 +
|7
 +
|-
 +
|''Tupã''
 +
|7
 +
|-
 +
|''t''
 +
|7
 +
|}
  
 
=Notes=
 
=Notes=

Revision as of 01:20, 17 February 2017

Transducer for Guarani (Work in progress).

Evaluation

The current corpus coverage is 2.85% (out of 1016 tokenized words in the corpus).

The most missed words were:

Class tags
Word Occurences
ha 44
a 43
va 41
pe 27
i
e 25
e 20
m 18
ra 17
ta 10
o 10
guarani 9
up 9
ñe 9
yvy 9
y 9
icha 9
me 8
rã 7
Tupã 7
t 7

Notes

Links

The transducer is available on Github.

Retrieved from "http://wikis.swarthmore.edu/ling073/index.php?title=Guarani/Transducer&oldid=2782"