Design challenges and misconceptions in named entity recognition

Design challenges and misconceptions in named entity recognition (2009)

by Lev Ratinov , Dan Roth

Venue:	PROCEEDINGS OF THE THIRTEENTH CONFERENCE ON COMPUTATIONAL NATURAL LANGUAGE LEARNING (CONLL)
Citations:	23 - 3 self

User correction supplied by larsmans

Datum	Value	Source
TITLE	Design challenges and misconceptions in named entity recognition	INFERENCE
AUTHOR NAME	Lev Ratinov	user correction
AUTHOR AFFIL	Computer Science Department; University of Illinois	user correction
AUTHOR ADDR	Urbana, IL 61801 USA	user correction
AUTHOR NAME	Dan Roth	user correction
AUTHOR AFFIL	Computer Science Department; University of Illinois	user correction
AUTHOR ADDR	Urbana, IL 61801 USA	user correction
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.	user correction
YEAR	2009	INFERENCE
VENUE	PROCEEDINGS OF THE THIRTEENTH CONFERENCE ON COMPUTATIONAL NATURAL LANGUAGE LEARNING (CONLL)	user correction
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	147--155	user correction
CITATIONS	31 found	ParsCit 1.0