A maximum entropy approach to natural language processing
Computational Linguistics
Learning dictionaries for information extraction by multi-level bootstrapping
AAAI '99/IAAI '99 Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence
Wrapper induction: efficiency and expressiveness
Artificial Intelligence - Special issue on Intelligent internet systems
Maximum Entropy Markov Models for Information Extraction and Segmentation
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Information Extraction with HMM Structures Learned by Stochastic Optimization
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Active Hidden Markov Models for Information Extraction
IDA '01 Proceedings of the 4th International Conference on Advances in Intelligent Data Analysis
Named entity recognition with a maximum entropy approach
CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Hi-index | 0.00 |
Text information extraction is an important approach to process large quantity of text. Since the traditional training method of hidden Markov model for text information extraction is sensitive to initial model parameters and easy to converge to a local optimal model in practice, a novel algorithm using hidden Markov model based on maximal entropy for text information extraction is presented. The new algorithm combines the advantage of maximum entropy model, which can integrate and process rules and knowledge efficiently, with that of hidden Markov model, which has powerful technique foundations to solve sequence representation and statistical problem. And the algorithm uses the sum of all features with weights to adjust the transition parameters in hidden Markov model for text information extraction. Experimental results show that compared with the simple hidden Markov model, the new algorithm improves the performance in precision and recall.