HAL: hal-00699295, version 1

Detailed view

Export this paper BibTeX - EndNote - TEI - RefWorks -

EACL 2012 Workshop on Innovative hybrid approaches to the processing of textual data, Avignon : France (2012)

A Joint Named Entity Recognition and Entity Linking System

Rosa Stern (  Corresponding author ) 1, Benoît Sagot 1, Frédéric Béchet 2

(2012-04)

We present a joint system for named entity recognition (NER) and entity linking (EL), allowing for named entities mentions ex- tracted from textual data to be matched to uniquely identifiable entities. Our approach relies on combined N E R modules which transfer the disambiguation step to the EL component, where referential knowledge about entities can be used to select a correct entity reading. Hybridation is a main fea- ture of our system, as we have performed experiments combining two types of NER, based respectively on symbolic and statis- tical techniques. Furthermore, the statisti- cal EL module relies on entity knowledge acquired over a large news corpus using a simple rule-base disambiguation tool. An implementation of our system is described, along with experiments and evaluation re- sults on French news wires. Linking ac- curacy reaches up to 87%, and the NER f- measure up to 83%.

1:	ALPAGE (INRIA Rocquencourt)
	INRIA – Université Paris VII - Paris Diderot
2:	Laboratoire d'informatique Fondamentale de Marseille (LIF)
	CNRS : UMR6166 – Université de la Méditerranée - Aix-Marseille II – Université de Provence - Aix-Marseille I

Subject

:

Computer Science/Computation and Language

Keyword(s): entity linking – statistical NER – symbolic NER

hal-00699295, version 1

http://hal.archives-ouvertes.fr/hal-00699295

oai:hal.archives-ouvertes.fr:hal-00699295

From: Rosa Stern <>

Submitted on: Sunday, 20 May 2012 15:28:48

Updated on: Monday, 21 May 2012 09:41:05