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

From Apertium
Jump to navigation Jump to search
Line 12: Line 12:
 
! <small>24,144</small> !! <small>21,247</small> !! <small>20,128</small> !! <small>10,171</small> !! <small>4,348</small> !! <small>3,823 </small> !! <small>239</small>
 
! <small>24,144</small> !! <small>21,247</small> !! <small>20,128</small> !! <small>10,171</small> !! <small>4,348</small> !! <small>3,823 </small> !! <small>239</small>
 
|-
 
|-
| '''1st''' ||align=right| 81.66 ||align=right| 86.18 ||align=right| 75.22 ||align=right| 75.63 ||align=right| 80.79||align=right| 61.53 ||align=right| 72.90
+
| '''1st''' ||align=right| 81.66 ||align=right| 86.23 ||align=right| 75.22 ||align=right| 75.63 ||align=right| 80.79||align=right| 61.53 ||align=right| 72.90
 
|-
 
|-
 
| '''CG→1st''' ||align=right| 83.79 ||align=right| 87.35 ||align=right| 79.67 ||align=right| 79.52 ||align=right| 86.19 ||align=right| 63.33 ||align=right| 73.86
 
| '''CG→1st''' ||align=right| 83.79 ||align=right| 87.35 ||align=right| 79.67 ||align=right| 79.52 ||align=right| 86.19 ||align=right| 63.33 ||align=right| 73.86
 
|-
 
|-
| '''Unigram model 1''' ||align=right| 91.72±1.37 ||||||||||align=right| 63.03±3.27
+
| '''Unigram model 1''' ||align=right| 91.72±1.37 ||align=right| 91.41±1.31 ||||||||align=right| 63.03±3.27
 
|-
 
|-
| '''CG→Unigram model 1''' ||align=right| 92.37±1.33 ||align=right| 92.03±1.63 ||||||||align=right| 63.29±3.24
+
| '''CG→Unigram model 1''' ||align=right| 92.37±1.33 ||align=right| 92.52±1.18 ||||||||align=right| 63.29±3.24
 
|-
 
|-
| '''Unigram model 2''' ||align=right| 91.78±1.30 ||||||||||align=right| 63.23±3.41
+
| '''Unigram model 2''' ||align=right| 91.78±1.30 ||align=right| 91.03±1.25 ||||||||align=right| 63.23±3.41
 
|-
 
|-
| '''CG→Unigram model 2''' ||align=right| 92.06±1.30 ||||||||||align=right| 63.16±3.17
+
| '''CG→Unigram model 2''' ||align=right| 92.06±1.30 ||align=right| 91.94±1.10 ||||||||align=right| 63.16±3.17
 
|-
 
|-
| '''Unigram model 3''' ||align=right| 91.74±1.29 ||||||||||align=right| 63.23±3.41
+
| '''Unigram model 3''' ||align=right| 91.74±1.29 ||align=right| 91.01±1.25 ||||||||align=right| 63.23±3.41
 
|-
 
|-
| '''CG→Unigram model 3''' ||align=right| 92.03±1.29 ||||||||||align=right| 63.16±3.17
+
| '''CG→Unigram model 3''' ||align=right| 92.03±1.29 ||align=right| 91.91±1.08 ||||||||align=right| 63.16±3.17
 
|-
 
|-
| '''Bigram (unsup, 0 iters)''' ||align=right| 85.05±1.22 ||||||||||align=right| 62.99±3.11
+
| '''Bigram (unsup, 0 iters)''' ||align=right| 85.05±1.22 ||align=right| 83.60±1.94 ||||||||align=right| 62.99±3.11
 
|-
 
|-
| '''Bigram (unsup, 50 iters)''' ||align=right| 88.81±1.36 ||||||||||align=right| 61.31±3.43
+
| '''Bigram (unsup, 50 iters)''' ||align=right| 88.81±1.36 ||align=right| 87.37±2.03 ||||||||align=right| 61.31±3.43
 
|-
 
|-
| '''Bigram (unsup, 250 iters)''' ||align=right| 88.53±1.35 ||||||||||align=right| 61.21±3.50
+
| '''Bigram (unsup, 250 iters)''' ||align=right| 88.53±1.35 ||align=right| 86.99±2.03 ||||||||align=right| 61.21±3.50
 
|-
 
|-
| '''CG→Bigram (unsup, 0 iters)''' ||align=right| 88.96±1.21 ||||||||||align=right| 63.01±3.23
+
| '''CG→Bigram (unsup, 0 iters)''' ||align=right| 88.96±1.21 ||align=right| 87.76±1.82 ||||||||align=right| 63.01±3.23
 
|-
 
|-
 
| '''CG→Bigram (unsup, 50 iters)''' ||align=right| 90.77±1.68 ||align=right| 89.34±1.71 ||||||||align=right| 62.82±3.26
 
| '''CG→Bigram (unsup, 50 iters)''' ||align=right| 90.77±1.68 ||align=right| 89.34±1.71 ||||||||align=right| 62.82±3.26
 
|-
 
|-
| '''CG→Bigram (unsup, 250 iters)''' ||align=right| 90.54±1.67 ||||||||||align=right| 62.82±3.26
+
| '''CG→Bigram (unsup, 250 iters)''' ||align=right| 90.54±1.67 ||align=right| 89.33±1.71 ||||||||align=right| 62.82±3.26
 
|-
 
|-
| '''Bigram (sup, 0 iters)''' ||align=right| 94.60±1.06 ||||||||||align=right| 63.14±3.24
+
| '''Bigram (sup, 0 iters)''' ||align=right| 94.60±1.06 ||align=right| 93.52±1.46 ||||||||align=right| 63.14±3.24
 
|-
 
|-
 
| '''Bigram (sup, 50 iters)''' ||align=right| 91.82±1.08 ||align=right| 91.32±1.71 ||||||||align=right| 62.97±3.57
 
| '''Bigram (sup, 50 iters)''' ||align=right| 91.82±1.08 ||align=right| 91.32±1.71 ||||||||align=right| 62.97±3.57
 
|-
 
|-
| '''Bigram (sup, 250 iters)''' ||align=right| 91.43±1.29 ||||||||||align=right| 62.94±3.61
+
| '''Bigram (sup, 250 iters)''' ||align=right| 91.43±1.29 ||align=right| 90.73±1.85 ||||||||align=right| 62.94±3.61
 
|-
 
|-
| '''CG→Bigram (sup, 0 iters)''' ||align=right| 94.62±1.38 ||||||||||align=right| 63.09±3.37
+
| '''CG→Bigram (sup, 0 iters)''' ||align=right| 94.62±1.38 ||align=right| 92.70±1.60 ||||||||align=right| 63.09±3.37
 
|-
 
|-
 
| '''CG→Bigram (sup, 50 iters)''' ||align=right| 92.31±1.28 ||align=right| 91.61±1.54 ||||||||align=right| 63.05±3.45
 
| '''CG→Bigram (sup, 50 iters)''' ||align=right| 92.31±1.28 ||align=right| 91.61±1.54 ||||||||align=right| 63.05±3.45
Line 52: Line 52:
 
| '''CG→Bigram (sup, 250 iters)''' ||align=right| 92.02±1.43 ||align=right| 91.55±1.54 ||||||||align=right| 63.02±3.48
 
| '''CG→Bigram (sup, 250 iters)''' ||align=right| 92.02±1.43 ||align=right| 91.55±1.54 ||||||||align=right| 63.02±3.48
 
|-
 
|-
| '''Lwsw (0 iters)''' ||align=right| 90.16±1.00 ||||||||||align=right| 62.80±3.67
+
| '''Lwsw (0 iters)''' ||align=right| 90.16±1.00 ||align=right| 89.78±1.27 ||||||||align=right| 62.80±3.67
 
|-
 
|-
| '''Lwsw (50 iters)''' ||align=right| 90.51±0.98 ||||||||||align=right| 62.74±3.62
+
| '''Lwsw (50 iters)''' ||align=right| 90.51±0.98 ||align=right| 89.98±1.38 ||||||||align=right| 62.74±3.62
 
|-
 
|-
 
| '''Lwsw (250 iters)''' ||align=right| 90.51±0.98 ||align=right| 90.06±1.39 ||||||||align=right| 62.74±3.62
 
| '''Lwsw (250 iters)''' ||align=right| 90.51±0.98 ||align=right| 90.06±1.39 ||||||||align=right| 62.74±3.62
 
|-
 
|-
| '''CG→Lwsw (0 iters)''' ||align=right| 90.78±1.26 ||||||||||align=right| 62.73±3.55
+
| '''CG→Lwsw (0 iters)''' ||align=right| 90.78±1.26 ||align=right| 89.61±1.43 ||||||||align=right| 62.73±3.55
 
|-
 
|-
| '''CG→Lwsw (50 iters)''' ||align=right| 91.05±1.21 ||||||||||align=right| 62.73±3.55
+
| '''CG→Lwsw (50 iters)''' ||align=right| 91.05±1.21 ||align=right| 89.63±1.56 ||||||||align=right| 62.73±3.55
 
|-
 
|-
 
| '''CG→Lwsw (250 iters)''' ||align=right| 91.06±1.25 ||align=right| 89.67±1.58 ||||||||align=right| 62.73±3.55
 
| '''CG→Lwsw (250 iters)''' ||align=right| 91.06±1.25 ||align=right| 89.67±1.58 ||||||||align=right| 62.73±3.55
Line 68: Line 68:
 
| '''CG→kaz-tagger''' ||
 
| '''CG→kaz-tagger''' ||
 
|}
 
|}
 
   
 
In the following table, the intervals represent the [low, high] values from 10-fold cross validation.
 
In the following table, the intervals represent the [low, high] values from 10-fold cross validation.

Revision as of 08:51, 28 May 2016

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.

In the following table values of the form x±y are the sample mean and standard deviation of the results of 10-fold cross validation.

System Language
Catalan Spanish Serbo-Croatian Russian Kazakh Portuguese Swedish
24,144 21,247 20,128 10,171 4,348 3,823 239
1st 81.66 86.23 75.22 75.63 80.79 61.53 72.90
CG→1st 83.79 87.35 79.67 79.52 86.19 63.33 73.86
Unigram model 1 91.72±1.37 91.41±1.31 63.03±3.27
CG→Unigram model 1 92.37±1.33 92.52±1.18 63.29±3.24
Unigram model 2 91.78±1.30 91.03±1.25 63.23±3.41
CG→Unigram model 2 92.06±1.30 91.94±1.10 63.16±3.17
Unigram model 3 91.74±1.29 91.01±1.25 63.23±3.41
CG→Unigram model 3 92.03±1.29 91.91±1.08 63.16±3.17
Bigram (unsup, 0 iters) 85.05±1.22 83.60±1.94 62.99±3.11
Bigram (unsup, 50 iters) 88.81±1.36 87.37±2.03 61.31±3.43
Bigram (unsup, 250 iters) 88.53±1.35 86.99±2.03 61.21±3.50
CG→Bigram (unsup, 0 iters) 88.96±1.21 87.76±1.82 63.01±3.23
CG→Bigram (unsup, 50 iters) 90.77±1.68 89.34±1.71 62.82±3.26
CG→Bigram (unsup, 250 iters) 90.54±1.67 89.33±1.71 62.82±3.26
Bigram (sup, 0 iters) 94.60±1.06 93.52±1.46 63.14±3.24
Bigram (sup, 50 iters) 91.82±1.08 91.32±1.71 62.97±3.57
Bigram (sup, 250 iters) 91.43±1.29 90.73±1.85 62.94±3.61
CG→Bigram (sup, 0 iters) 94.62±1.38 92.70±1.60 63.09±3.37
CG→Bigram (sup, 50 iters) 92.31±1.28 91.61±1.54 63.05±3.45
CG→Bigram (sup, 250 iters) 92.02±1.43 91.55±1.54 63.02±3.48
Lwsw (0 iters) 90.16±1.00 89.78±1.27 62.80±3.67
Lwsw (50 iters) 90.51±0.98 89.98±1.38 62.74±3.62
Lwsw (250 iters) 90.51±0.98 90.06±1.39 62.74±3.62
CG→Lwsw (0 iters) 90.78±1.26 89.61±1.43 62.73±3.55
CG→Lwsw (50 iters) 91.05±1.21 89.63±1.56 62.73±3.55
CG→Lwsw (250 iters) 91.06±1.25 89.67±1.58 62.73±3.55
kaz-tagger
CG→kaz-tagger

In the following table, the intervals represent the [low, high] values from 10-fold cross validation.

Language Corpus System
Sent Tok Amb 1st CG+1st Unigram CG+Unigram apertium-tagger CG+apertium-tagger
Catalan 1,413 24,144 ? 81.85 83.96 [75.65, 78.46] [87.76, 90.48] [94.16, 96.28] [93.92, 96.16]
Spanish 1,271 21,247 ? 86.18 86.71 [78.20, 80.06] [87.72, 90.27] [90.15, 94.86] [91.84, 93.70]
Serbo-Croatian 1,190 20,128 ? 75.22 79.67 [75.36, 78.79] [75.36, 77.28]
Russian 451 10,171 ? 75.63 79.52 [70.49, 72.94] [74.68, 78.65] n/a n/a
Kazakh 403 4,348 ? 80.79 86.19 [84.36, 87.79] [85.56, 88.72] n/a n/a
Portuguese 119 3,823 ? 72.54 87.34 [77.10, 87.72] [84.05, 91.96]
Swedish 11 239 ? 72.90 73.86 [56.00, 82.97]

Sent = sentences, Tok = tokens, Amb = average ambiguity from the morphological analyser

Systems

  • 1st: Selects the first analysis from the morphological analyser
  • CG: Uses the CG (from the monolingual language package in languages) to preprocess the input.
  • Unigram: Lexicalised unigram tagger
  • apertium-tagger: Uses the bigram HMM tagger included with Apertium.

Corpora

The tagged corpora used in the experiments are found in the monolingual packages in languages, under the texts/ subdirectory.

Todo