Language independent NER using a unified model of internal and contextual evidence

Open Access

1 January 2002

conference paper
Published by Association for Computational Linguistics (ACL)

p. 1-4
https://doi.org/10.3115/1118853.1118860

Abstract

This paper investigates the use of a language independent model for named entity recognition based on iterative learning in a co-training fashion, using word-internal and contextual information as independent evidence sources. Its bootstrapping process begins with only seed entities and seed contexts extracted from the provided annotated corpus. F-measure exceeds 77 in Spanish and 72 in Dutch.

Keywords

SEED ENTITY
ITERATIVE LEARNING
CO-TRAINING FASHION
ANNOTATED CORPUS
LANGUAGE INDEPENDENT NER
CONTEXTUAL INFORMATION
BOOTSTRAPPING PROCESS
INDEPENDENT EVIDENCE SOURCE
CONTEXTUAL EVIDENCE
UNIFIED MODEL
ENTITY RECOGNITION
LANGUAGE INDEPENDENT MODEL
SPANISH LANGUAGE
ITERATIONS
FOREIGN LANGUAGES
ALGORITHMS
LANGUAGE
CORES
EXTRACTION

This publication has 0 references indexed in Scilit: