Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Convergence rates of the Voting Gibbs classifier, with application to Bayesian feature selection
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Transforming classifier scores into accurate multiclass probability estimates
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Three new probabilistic models for dependency parsing: an exploration
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
ICML '04 Proceedings of the twenty-first international conference on Machine learning
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Online large-margin training of dependency parsers
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
EMNLP '06 Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing
Confidence estimation for information extraction
HLT-NAACL-Short '04 Proceedings of HLT-NAACL 2004: Short Papers
Joint parsing and semantic role labeling
CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning
Convolution kernel over packed parse forest
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Joint training and decoding using virtual nodes for cascaded segmentation and tagging tasks
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
We're not in Kansas anymore: detecting domain changes in streams
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Task optimization based on CPU pipeline technique in a multicore system
Computers & Mathematics with Applications
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Part-of-speech tagging for Chinese-English mixed texts with dynamic features
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
Beyond myopic inference in big data pipelines
Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
Hi-index | 0.01 |
We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores associated with outputs at any given stage in a pipeline in order to compute probabilistic features used at other stages downstream. We describe a simple method of integrating probabilistic features into the linear scoring functions used by state of the art machine learning algorithms. Experimental evaluation on dependency parsing and named entity recognition demonstrate the superiority of our approach over the baseline pipeline models, especially when upstream stages in the pipeline exhibit low accuracy.