Robust Information Extraction with Perceptrons
作者： Mihai Surdeanu , Massimiliano Ciaramita
DOI:
关键词:
摘要: We present a system for the extraction of entity and relation mentions. Our work focused on robustness simplicity: all components are modeled using variants Perceptron algorithm (Rosemblatt, 1858) only partial syntactic information is used feature extraction. approach has two novel ideas. First, we define new large-margin tailored classunbalanced data which dynamically adjusts its margins, according to generalization performance model. Second, propose architecture that lets classification ambiguities flow through solves them at end. The achieves competitive accuracy ACE English EMD RMD tasks.
surdeanu.info 参考文章(16)
Y Altun, T Hofmann, M. Collins M. Steedman, M Johnson, Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences empirical methods in natural language processing. pp. 145- 152 ,(2003)
Alberto Lavelli, Lorenza Romano, Claudio Giuliano, Exploiting Shallow Linguistic Information for Relation Extraction from Biomedical Literature conference of the european chapter of the association for computational linguistics. ,(2006)
Ralf Herbrich, Hugo Zaragoza, Yaoyong Li, John Shawe-Taylor, Jaz S. Kandola, The Perceptron Algorithm with Uneven Margins international conference on machine learning. pp. 379- 386 ,(2002)
Christopher M. Bishop, Neural networks for pattern recognition ,(1995)
Wen-tau Yih, Dan Roth, A Linear Programming Formulation for Global Inference in Natural Language Tasks conference on computational natural language learning. pp. 1- 8 ,(2004)
Nello Cristianini, J Shawe-Taylor, An introduction to Support Vector Machines Cambridge University Press (2000). ,(2000)
Andrew McCallum, Dayne Freitag, Fernando C. N. Pereira, Maximum Entropy Markov Models for Information Extraction and Segmentation international conference on machine learning. pp. 591- 598 ,(2000)
Yoav Freund, Robert E. Schapire, Large margin classification using the perceptron algorithm conference on learning theory. ,vol. 37, pp. 209- 217 ,(1998) , 10.1145/279943.279985
Michael Collins, Discriminative training methods for hidden Markov models: theory and experiments with perceptron algorithms empirical methods in natural language processing. pp. 1- 8 ,(2002) , 10.3115/1118693.1118694
Adam Kilgarriff, Christiane Fellbaum, WordNet : an electronic lexical database Language. ,vol. 76, pp. 706- ,(2000) , 10.2307/417141