Wrapping up a Summary: from Representation to Generation

Wrapping up a Summary: from Representation to Generation

The main focus of this work is to investigaterobust ways for generating summariesfrom summary representations without recurringto simple sentence extraction andaiming at more human-like summaries.This is motivated by empirical evidencefrom TAC 2009 data showing that humansummaries contain on average more andshorter sentences than the system summaries.We report encouraging preliminaryresults comparable to those attainedby participating systems at TAC 2009.

Keywords: Summary generation, summarization, TAC

Year: 2010

Download: download 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:


Project

Automatic Text Summarisation

Authors:  Josef Steinberger, Karel Je┼żek, Michal Campr, Ji┼Ö├ş Hynek
Desc.:Automatic text summarisation using various text mining methods, mainly Latent Semantic Analysis (LSA).