Difference between revisions of "Guarani and Warlpiri"

From LING073
Jump to: navigation, search
(→‎gug → wbp Evaluation)
(→‎gug → wbp Evaluation)
Line 39: Line 39:
 
==gug → wbp Evaluation==
 
==gug → wbp Evaluation==
 
===Results when running on tests===
 
===Results when running on tests===
−
*Number of unknown words: 4
+
*Number of unknown words: 0
−
*Percentage of unknown words: 28.57%
+
*Percentage of unknown words: 0%
  
 
When removing unknown words:
 
When removing unknown words:
−
*WER = 78.57%
+
*WER = 92.86%
−
*PER = 78.57%
+
*PER = 92.86%
 
When unknown words are not removed:
 
When unknown words are not removed:
−
*WER = 100%
+
*WER = 92.86%
−
*PER = 100%
+
*PER = 92.86%
 +
 
 
===Results when running on sentences (corpus) ===
 
===Results when running on sentences (corpus) ===
 +
*Number of unknown words: 120
 +
*Percentage of unknown words: 206.90%
 +
 
When removing unknown words:
 
When removing unknown words:
−
*WER = 22.41%
+
*WER = 0.0%
−
*PER = 22.41%
+
*PER = 0.0%
 
When unknown words are not removed:
 
When unknown words are not removed:
 
*WER = 100%
 
*WER = 100%

Revision as of 00:43, 26 March 2017

Resources for machine translation between Guarani and Warlpiri

Corpora

wbp -> gug evaluation

Results when running on tests

  • Number of unknown words: 4
  • Percentage of unknown words: 28.57%

When removing unknown words:

  • WER = 78.57%
  • PER = 78.57%

When unknown words are not removed:

  • WER = 100%
  • PER = 100%

Results when running on sentences (corpus)

When removing unknown words:

  • WER = 22.41%
  • PER = 22.41%

When unknown words are not removed:

  • WER = 100%
  • PER = 100%

Developed Resources

Lexical Selection

gug → wbp Evaluation

Results when running on tests

  • Number of unknown words: 0
  • Percentage of unknown words: 0%

When removing unknown words:

  • WER = 92.86%
  • PER = 92.86%

When unknown words are not removed:

  • WER = 92.86%
  • PER = 92.86%

Results when running on sentences (corpus)

  • Number of unknown words: 120
  • Percentage of unknown words: 206.90%

When removing unknown words:

  • WER = 0.0%
  • PER = 0.0%

When unknown words are not removed:

  • WER = 100%
  • PER = 100%