Neural Networks for Featureless Named Entity Recognition in Czech
作者： Jana Straková , Milan Straka , Jan Hajič
DOI: 10.1007/978-3-319-45510-5_20
关键词:
摘要: We present a completely featureless, language agnostic named entity recognition system. Following recent advances in artificial neural network research, the recognizer employs parametric rectified linear units (PReLU), word embeddings and character-level based on gated (GRU). Without any feature engineering, only with surface forms, lemmas tags as input, achieves excellent results Czech NER surpasses current state of art previously published systems, which use manually designed rule-based orthographic classification features. Furthermore, robust even when forms are available input. In addition, proposed can features such combination, it exceeds by wide margin.
springer.com
sci-hub.se 参考文章(28)
Michal Konkol, Miloslav Konopík, CRF-Based Czech Named Entity Recognizer and Consolidation of Czech NER Research text speech and dialogue. ,vol. 8082, pp. 153- 160 ,(2013) , 10.1007/978-3-642-40585-3_20
Jana Straková, Milan Straka, Jan Hajič, A New State-of-The-Art Czech Named Entity Recognizer text speech and dialogue. pp. 68- 75 ,(2013) , 10.1007/978-3-642-40585-3_10
Ronan Collobert, Clément Farabet, Koray Kavukcuoglu, Torch7: A Matlab-like Environment for Machine Learning neural information processing systems. ,(2011)
Magda Ševčíková, Zdeněk Žabokrtský, Oldřich Krůza, Named entities in Czech: annotating data and developing NE tagger text speech and dialogue. pp. 188- 195 ,(2007) , 10.1007/978-3-540-74628-7_26
Michal Konkol, Tomáš Brychcín, Miloslav Konopík, Latent semantics in Named Entity Recognition Expert Systems With Applications. ,vol. 42, pp. 3470- 3479 ,(2015) , 10.1016/J.ESWA.2014.12.015
Lev Ratinov, Dan Roth, Design Challenges and Misconceptions in Named Entity Recognition conference on computational natural language learning. pp. 147- 155 ,(2009) , 10.3115/1596374.1596399
Hakan Demir, Arzucan Ozgur, Improving Named Entity Recognition for Morphologically Rich Languages Using Word Embeddings international conference on machine learning and applications. pp. 117- 122 ,(2014) , 10.1109/ICMLA.2014.24
Sepp Hochreiter, Jürgen Schmidhuber, Long short-term memory Neural Computation. ,vol. 9, pp. 1735- 1780 ,(1997) , 10.1162/NECO.1997.9.8.1735
Alex Graves, Jürgen Schmidhuber, 2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures Neural Networks. ,vol. 18, pp. 602- 610 ,(2005) , 10.1016/J.NEUNET.2005.06.042
Jana Kravalová, Zdeněk Žabokrtský, None, Czech Named Entity Corpus and SVM-based Recognizer Proceedings of the 2009 Named Entities Workshop: Shared Task on Transliteration (NEWS 2009). pp. 194- 201 ,(2009) , 10.3115/1699705.1699748