Difference between revisions of "POS Tagging (State of the art)"

From ACL Wiki
Jump to: navigation, search
(References)
(Added WSJ results for MElt (Denis and Sagot 2009), originally developed for French. Fair overall results, good results on unknown words.)
Line 28: Line 28:
 
| 96.46%
 
| 96.46%
 
| 85.86%
 
| 85.86%
 +
|-
 +
| MElt
 +
| MEMM with external lexical information
 +
| Denis and Sagot (2009)
 +
| [https://gforge.inria.fr/projects/lingwb/]
 +
| No
 +
| 96.96%
 +
| 91.29%
 
|-
 
|-
 
| GENiA Tagger**
 
| GENiA Tagger**
Line 129: Line 137:
  
 
* Collins, Michael. 2002. [http://people.csail.mit.edu/mcollins/papers/tagperc.pdf Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms]. ''EMNLP 2002''.
 
* Collins, Michael. 2002. [http://people.csail.mit.edu/mcollins/papers/tagperc.pdf Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms]. ''EMNLP 2002''.
 +
 +
* Denis, Pascal and Sagot, Benoît. 2009. [http://alpage.inria.fr/~sagot/pub/paclic09tagging.pdf Coupling an annotated corpus and a morphosyntactic lexicon for state-of-the-art POS tagging with less human effort]. "PACLIC 2009"
  
 
* Giménez, J., and Márquez, L. 2004. [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.  
 
* Giménez, J., and Márquez, L. 2004. [http://www.lsi.upc.es/~nlp/SVMTool/lrec2004-gm.pdf SVMTool: A general POS tagger generator based on Support Vector Machines]. ''Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC'04)''. Lisbon, Portugal.  

Revision as of 03:27, 29 March 2012

Test collections

  • Performance measure: per token accuracy. (The convention is for this to be measured on all tokens, including punctuation tokens and other unambiguous tokens.)
  • English
    • Penn Treebank Wall Street Journal (WSJ) release 3 (LDC99T42). The splits of data for this task were not standardized early on (unlike for parsing) and early work uses various data splits defined by counts of tokens or by sections. Most work from 2002 on adopts the following data splits, introduced by Collins (2002):
      • Training data: sections 0-18
      • Development test data: sections 19-21
      • Testing data: sections 22-24

Tables of results

WSJ

System name Short description Main publication Software Extra Data?*** All tokens Unknown words
TnT* Hidden markov model Brants (2000) TnT No 96.46% 85.86%
MElt MEMM with external lexical information Denis and Sagot (2009) [1] No 96.96% 91.29%
GENiA Tagger** Maximum entropy cyclic dependency network Tsuruoka, et al (2005) GENiA No 97.05% Not available
Averaged Perceptron Averaged Perception discriminative sequence model Collins (2002) Not available No 97.11% Not available
Maxent easiest-first Maximum entropy bidirectional easiest-first inference Tsuruoka and Tsujii (2005) Easiest-first No 97.15% Not available
SVMTool SVM-based tagger and tagger generator Giménez and Márquez (2004) SVMTool No 97.16% 89.01%
Morče/COMPOST Averaged Perceptron Spoustová et al. (2009) [2] No 97.23% Not available
Stanford Tagger 1.0 Maximum entropy cyclic dependency network Toutanova et al. (2003) Stanford Tagger No 97.24% 89.04%
Stanford Tagger 2.0 Maximum entropy cyclic dependency network Manning (2011) Stanford Tagger No 97.29% 89.70%
Stanford Tagger 2.0 Maximum entropy cyclic dependency network Manning (2011) Stanford Tagger Yes 97.32% 90.79%
LTAG-spinal Bidirectional perceptron learning Shen et al. (2007) LTAG-spinal No 97.33% Not available
Morče/COMPOST Averaged Perceptron Spoustová et al. (2009) [3] Yes 97.44% Not available
SCCN Semi-supervised condensed nearest neighbor Søgaard (2011) SCCN Yes 97.50% Not available

(*) TnT: Accuracy is as reported by Giménez and Márquez (2004) for the given test collection. Brants (2000) reports 96.7% token accuracy and 85.5% unknown word accuracy on a 10-fold cross-validation of the Penn WSJ corpus.

(**) GENiA: Results are for models trained and tested on the given corpora (to be comparable to other results). The distributed GENiA tagger is trained on a mixed training corpus and gets 96.94% on WSJ, and 98.26% on GENiA biomedical English.

(***) Extra data: Whether system training exploited (usually large amounts of) extra unlabeled text, such as by semi-supervised learning, self-training, or using distributional similarity features, beyond the standard supervised training data.

References

  • Manning, Christopher D. 2011. Part-of-Speech Tagging from 97% to 100%: Is It Time for Some Linguistics? In Alexander Gelbukh (ed.), Computational Linguistics and Intelligent Text Processing, 12th International Conference, CICLing 2011, Proceedings, Part I. Lecture Notes in Computer Science 6608, pp. 171--189. Springer.
  • Søgaard, Anders. 2011. Semi-supervised condensed nearest neighbor for part-of-speech tagging. The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT). Portland, Oregon.
  • Spoustová, Drahomíra "Johanka", Jan Hajič, Jan Raab and Miroslav Spousta. 2009. Semi-supervised Training for the Averaged Perceptron POS Tagger. Proceedings of the 12 EACL, pages 763-771.

See also