Difference between revisions of "Comparison of part-of-speech tagging systems"

From Apertium
Jump to navigation Jump to search
Line 1: Line 1:
 
{{TOCD}}
 
{{TOCD}}
   
  +
Apertium would like to have really good part-of-speech tagging, but in many cases falls below the state-of-the-art (around 97% tagging accuracy). This page intends to collect a comparison of tagging systems in Apertium and give some ideas of what could be done to improve them.
   
 
{|class=wikitable
 
{|class=wikitable
 
!rowspan=2|Language !!colspan=6|System
 
!rowspan=2|Language !!colspan=6|System
 
|-
 
|-
! 1st !! CG+1st !! Unigram || CG+Unigram || apertium-tagger || CG+apertium-tagger
+
! 1st !! CG+1st !! Unigram || CG+Unigram || apertium-tagger || CG+apertium-tagger
 
|-
 
|-
 
| Catalan || 81.85 || 83.96 || [75.65, 78.46]|| [87.76, 90.48] || [94.16, 96.28] || [93.92, 96.16]
 
| Catalan || 81.85 || 83.96 || [75.65, 78.46]|| [87.76, 90.48] || [94.16, 96.28] || [93.92, 96.16]
 
|-
 
|-
| Spanish || 86.18 || 86.71 || [78.20, 80.06] || [87.72, 90.27] || ||
+
| Spanish || 86.18 || 86.71 || [78.20, 80.06] || [87.72, 90.27] || ||
 
|-
 
|-
| Kazakh || 80.25 || 86.13 || [83.55, 86.19] || [83.33, 86.61] || n/a || n/a
+
| Kazakh || 80.25 || 86.13 || [83.55, 86.19] || [83.33, 86.61] || n/a || n/a
 
|-
 
|-
 
|}
 
|}

Revision as of 16:27, 21 December 2015

Contents

Apertium would like to have really good part-of-speech tagging, but in many cases falls below the state-of-the-art (around 97% tagging accuracy). This page intends to collect a comparison of tagging systems in Apertium and give some ideas of what could be done to improve them.

Language System
1st CG+1st Unigram CG+Unigram apertium-tagger CG+apertium-tagger
Catalan 81.85 83.96 [75.65, 78.46] [87.76, 90.48] [94.16, 96.28] [93.92, 96.16]
Spanish 86.18 86.71 [78.20, 80.06] [87.72, 90.27]
Kazakh 80.25 86.13 [83.55, 86.19] [83.33, 86.61] n/a n/a


Todo