Highly Multilingual Coreference Resolution Exploiting a Mature Entity Repository
In this paper we present an approach tolarge-scale coreference resolution for anample set of human languages, with a particularemphasis on time performance andprecision. One of the distinctive featuresof our approach is the use of a maturemultilingual named entity repository (personsand organizations) gradually compiledover the past few years. Our experimentsshow promising results – an overallprecision of 94% tested on seven differentlanguages. We also present an extrinsicevaluation on seven languages inthe context of summarization where wegauge the contribution of the coreferenceresolver towards the end summarizationperformance.
Keywords: Coreference resolution, Named entity recognition, multilingual
Year: 2011
Download: 
Full text
Full text Authors of this publication:
Josef Steinberger
E-mail: jstein@kiv.zcu.cz
Josef is an associated professor at the Department of computer science and engineering at the University of West Bohemia in Pilsen, Czech Republic. He is interested in media monitoring and analysis, mainly automatic text summarisation, sentiment analysis and coreference resolution.
Related Projects:
Automatic Text Summarisation | |
| Authors: | Josef Steinberger, Karel Ježek, Michal Campr, Jiří Hynek |
| Desc.: | Automatic text summarisation using various text mining methods, mainly Latent Semantic Analysis (LSA). |