Segment Representations in Named Entity Recognition
作者： Michal Konkol , Miloslav Konopík
DOI: 10.1007/978-3-319-24033-6_7
关键词:
摘要: In this paper we study the effects of various segment representations in named entity recognition NER task. The representation is responsible for mapping multi-word entities into classes used chosen machine learning approach. Usually, choice a system arbitrary without proper tests. Some authors presented comparisons different such as BIO, BIEO, BILOU and usually compared only two representations. Our goal to show, that problem more complex selection best approach not straightforward. We provide experiments with wide set All are tested using popular algorithms: Conditional Random Fields Maximum Entropy. Furthermore, tests done on four languages, namely English, Spanish, Dutch Czech.
springer.com
sci-hub.se 参考文章(19)
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
Michal Konkol, Brainy: A Machine Learning Library Artificial Intelligence and Soft Computing. pp. 490- 499 ,(2014) , 10.1007/978-3-319-07176-3_43
Xinnian Mao, Saike He, Wei Xu, Yuan Dong, Haila Wang, Using Non-Local Features to Improve Named Entity Recognition Recall pacific asia conference on language information and computation. pp. 303- 310 ,(2007)
Ralph Grishman, Andrew Eliot Borthwick, A maximum entropy approach to named entity recognition Ph. D. Thesis New York University. ,(1999)
Hong Shen, Anoop Sarkar, Voting between multiple data representations for text chunking Lecture Notes in Computer Science. pp. 389- 400 ,(2005) , 10.1007/11424918_40
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
Han-Cheol Cho, Naoaki Okazaki, Makoto Miwa, Jun’ichi Tsujii, Named entity recognition with multiple segment representations Information Processing and Management. ,vol. 49, pp. 954- 965 ,(2013) , 10.1016/J.IPM.2013.03.002
Silviu Cucerzan, David Yarowsky, Language independent NER using a unified model of internal and contextual evidence international conference on computational linguistics. pp. 1- 4 ,(2002) , 10.3115/1118853.1118860
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