Design challenges and misconceptions in named entity recognition
L. Ratinov, and D. Roth. CoNLL '09: Proceedings of the Thirteenth Conference on Computational Natural Language Learning, page 147--155. Morristown, NJ, USA, Association for Computational Linguistics, (2009)
Abstract
We analyze some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system. In particular, we address issues such as the representation of text chunks, the inference approach needed to combine local NER decisions, the sources of prior knowledge and how to use them within an NER system. In the process of comparing several solutions to these challenges we reach some surprising conclusions, as well as develop an NER system that achieves 90.8 F1 score on the CoNLL-2003 NER shared task, the best reported result for this dataset.
Description
Design challenges and misconceptions in named entity recognition
%0 Conference Paper
%1 conf/CONLL/2009/RatinovRoth
%A Ratinov, Lev
%A Roth, Dan
%B CoNLL '09: Proceedings of the Thirteenth Conference on Computational Natural Language Learning
%C Morristown, NJ, USA
%D 2009
%I Association for Computational Linguistics
%K design entity misconceptions ner recognition
%P 147--155
%T Design challenges and misconceptions in named entity recognition
%U http://portal.acm.org/citation.cfm?id=1596399&dl=GUIDE,
%X We analyze some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system. In particular, we address issues such as the representation of text chunks, the inference approach needed to combine local NER decisions, the sources of prior knowledge and how to use them within an NER system. In the process of comparing several solutions to these challenges we reach some surprising conclusions, as well as develop an NER system that achieves 90.8 F1 score on the CoNLL-2003 NER shared task, the best reported result for this dataset.
%@ 978-1-932432-29-9
@inproceedings{conf/CONLL/2009/RatinovRoth,
abstract = {We analyze some of the fundamental design challenges and misconceptions that underlie the development of an efficient and robust NER system. In particular, we address issues such as the representation of text chunks, the inference approach needed to combine local NER decisions, the sources of prior knowledge and how to use them within an NER system. In the process of comparing several solutions to these challenges we reach some surprising conclusions, as well as develop an NER system that achieves 90.8 F1 score on the CoNLL-2003 NER shared task, the best reported result for this dataset.},
added-at = {2010-05-19T15:28:39.000+0200},
address = {Morristown, NJ, USA},
author = {Ratinov, Lev and Roth, Dan},
biburl = {https://www.bibsonomy.org/bibtex/2775dc1300283e2ac2fa8255f09370773/lama},
booktitle = {CoNLL '09: Proceedings of the Thirteenth Conference on Computational Natural Language Learning},
description = {Design challenges and misconceptions in named entity recognition},
interhash = {066fe8dcf46286bd1e406ff5a0983926},
intrahash = {775dc1300283e2ac2fa8255f09370773},
isbn = {978-1-932432-29-9},
keywords = {design entity misconceptions ner recognition},
location = {Boulder, Colorado},
pages = {147--155},
publisher = {Association for Computational Linguistics},
timestamp = {2010-05-19T15:28:39.000+0200},
title = {Design challenges and misconceptions in named entity recognition},
url = {http://portal.acm.org/citation.cfm?id=1596399&dl=GUIDE,},
year = 2009
}