Selective analysis for automatic abstracting: evaluating indicativeness and acceptability
Horacio Saggion, Guy Lapalme · 2000
ing: Evaluating Indicativeness and Acceptability Horacio Saggion and Guy Lapalme Departement d'Informatique et Recherche Operationnelle Universite de Montreal CP 6128, Succ Centre-Ville Montreal, Quebec, Canada, H3C 3J7 Fax: +1-514-343-5834 {saggion,lapalme}@iro.umontreal.ca Abstract We have developed a new methodology for automatic abstracting of scientific and technical articles called Selective Analysis. This methodology allows the generation of indicativeinformative abstracts integrating different types of information extracted from the source text. The indicative part of the abstract identifies the topics of the document while the informative one elaborates some topics according to the reader's interest. The first evaluation of our methodology demonstrates that Selective Analysis performs well in the task of signaling the topic of the document demonstrating the viability of such a technique. The sentences the system produces from instantiated templates are conside...