Machine Learning
Forgetting Exceptions is Harmful in Language Learning
Machine Learning - Special issue on natural language learning
Machine Learning
Combining Error-Driven Pruning and Classification for Partial Parsing
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
TnT: a statistical part-of-speech tagger
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Bagging and boosting a treebank parser
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
A simple rule-based part of speech tagger
ANLC '92 Proceedings of the third conference on Applied natural language processing
Memory-based learning: using similarity for smoothing
ACL '98 Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and Eighth Conference of the European Chapter of the Association for Computational Linguistics
Classifier combination for improved lexical disambiguation
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Error-driven pruning of Treebank grammars for base noun phrase identification
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Scaling to very very large corpora for natural language disambiguation
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Introduction to the CoNLL-2000 shared task: chunking
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Use of support vector learning for chunk identification
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Shallow parsing as part-of-speech tagging
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Single-classifier memory-based phrase chunking
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Introduction to special issue on machine learning approaches to shallow parsing
The Journal of Machine Learning Research
A comparison of algorithms for maximum entropy parameter estimation
COLING-02 proceedings of the 6th conference on Natural language learning - Volume 20
Active learning and logarithmic opinion pools for hpsg parse selection
Natural Language Engineering
Correcting dependency annotation errors
EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
Learning with annotation noise
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
Syntactic chunking across different corpora
MLMI'06 Proceedings of the Third international conference on Machine Learning for Multimodal Interaction
Hi-index | 0.00 |
Shallow parsers are usually assumed to be trained on noise-free material, drawn from the same distribution as the testing material. However, when either the training set is noisy or else drawn from a different distributions, performance may be degraded. Using the parsed Wall Street Journal, we investigate the performance of four shallow parsers (maximum entropy, memory-based learning, N-grams and ensemble learning) trained using various types of artificially noisy material. Our first set of results show that shallow parsers are surprisingly robust to synthetic noise, with performance gradually decreasing as the rate of noise increases. Further results show that no single shallow parser performs best in all noise situations. Final results show that simple, parser-specific extensions can improve noise-tolerance. Our second set of results addresses the question of whether naturally occurring disfluencies undermines performance more than does a change in distribution. Results using the parsed Switchboard corpus suggest that, although naturally occurring disfluencies might harm performance, differences in distribution between the training set and the testing set are more significant.