Class-based n-gram models of natural language
Computational Linguistics
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Tagging English text with a probabilistic model
Computational Linguistics
Distributional part-of-speech tagging
EACL '95 Proceedings of the seventh conference on European chapter of the Association for Computational Linguistics
Combining distributional and morphological information for part of speech induction
EACL '03 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics - Volume 1
Feature-rich part-of-speech tagging with a cyclic dependency network
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Contrastive estimation: training log-linear models on unlabeled data
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Prototype-driven learning for sequence models
HLT-NAACL '06 Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics
CoNLL-X shared task on multilingual dependency parsing
CoNLL-X '06 Proceedings of the Tenth Conference on Computational Natural Language Learning
Domain adaptation with structural correspondence learning
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
A comparison of Bayesian estimators for unsupervised Hidden Markov Model POS taggers
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Unsupervised multilingual learning for POS tagging
EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Minimized models for unsupervised part-of-speech tagging
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Wiktionary and NLP: improving synonymy networks
People's Web '09 Proceedings of the 2009 Workshop on The People's Web Meets NLP: Collaboratively Constructed Semantic Resources
Using Wikipedia and Wiktionary in domain-specific information retrieval
CLEF'08 Proceedings of the 9th Cross-language evaluation forum conference on Evaluating systems for multilingual and multimodal information access
Painless unsupervised learning with features
HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
SVD and clustering for unsupervised POS tagging
ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
Simple type-level unsupervised POS tagging
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Unsupervised part-of-speech tagging with bilingual graph-based projections
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Controlling complexity in part-of-speech induction
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
Despite significant recent work, purely unsupervised techniques for part-of-speech (POS) tagging have not achieved useful accuracies required by many language processing tasks. Use of parallel text between resource-rich and resource-poor languages is one source of weak supervision that significantly improves accuracy. However, parallel text is not always available and techniques for using it require multiple complex algorithmic steps. In this paper we show that we can build POS-taggers exceeding state-of-the-art bilingual methods by using simple hidden Markov models and a freely available and naturally growing resource, the Wiktionary. Across eight languages for which we have labeled data to evaluate results, we achieve accuracy that significantly exceeds best unsupervised and parallel text methods. We achieve highest accuracy reported for several languages and show that our approach yields better out-of-domain taggers than those trained using fully supervised Penn Treebank.