Aspects of Multilingual News Summarisation
In this book chapter, we discuss several pertinent aspects of an automatic system that generates summaries in multiple languages for sets of topic-related news articles (multilingual multi-document summarisation), gathered by news aggregation systems. The discussion follows a framework based on Latent Semantic Analysis (LSA) because LSA was shown to be a high-performing method across many different languages. Starting from a sentence-extractive approach we show how domain-specific aspects can be used and how a compression and paraphrasing method can be plugged in. We also discuss the challenging problem of summarisation evaluation in different languages. In particular, we describe two approaches: the first uses a parallel corpus and the second statistical machine translation.
STEINBERGER Josef;
TANEV Hristo;
STEINBERGER Ralf;
ZAVARELLA Vanni;
TURCHI Marco;
2014-01-27
IGI Global
JRC82759
978-1-4666-5019-0 (print),
978-1-4666-5020-6 (online),
2327-1981 (print),
2327-199X (online),
http://www.igi-global.com/book/innovative-document-summarization-techniques/84169,
https://publications.jrc.ec.europa.eu/repository/handle/JRC82759,
10.4018/978-1-4666-5019-0.ch012,
Additional supporting files
| File name | Description | File type | |
|---|
