LSA-Based Multi-Document Summarization

LSA-Based Multi-Document Summarization

We present our first multilingual multi-document summarizer. The proposed LSA-based method satisfies the multilinguality constraint because it works only with the context of terms. We experiment with Czech and English Corpora. The experiments show that the summarizer is comparable with the best DUC participated systems.

Keywords: Multi-document text summarization, latent semantic analysis

Year: 2007

Download: download Full text [87 kB]

Authors of this publication:

Josef Steinberger


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.

Martin Křišťan

Martin graduated at University of West Bohemia in 2007.

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).