Multilingual Summarization by Integrating Linguistic Resources in the MLIS-MUSI Project


Alessandro Lenci (Università di Pisa, Italy)

Roberto Bartolini (Istituto di Linguistica Computazionale, CNR, Pisa, Italy)

Nicoletta Calzolari (Istituto di Linguistica Computazionale, CNR, Pisa, Italy)

Ana Agua (DFKI GmbH3, Saarbrücken, Germany)

Stephan Busemann (DFKI GmbH3, Saarbrücken, Germany)

Emmanuel Cartier (Lingway, Ivry, France)

Karine Chevreau (Lingway, Ivry, France)

José Coch (Lingway, Ivry, France)


WO16: Applications Based On Written LRs


In this paper we will illustrate the approach to multilingual automatic abstract production adopted by the EU-sponsored project MLIS-MUSI. Although a small scale research project, MUSI has tried to tackle the challenges set by multilingual summarization by adopting an original approach based on the definition of a shared ontology and representation language, and on the reuse of existing linguistic resources. MUSI combines a linguistic-based module for relevant sentence extraction and a concept-based component to generate multilingual summaries.


Multilingual summarization, Resources integration, Text generation, Robust linguistic analysis

Full Paper