Segmenter et structurer thématiquement des textes par l'utilisation conjointe de collocations et de la récurrence lexicale

Olivier Ferret, Fontenay-aux-Roses Cedex · 2002

We present in this paper a method for achieving in an integrated way two tasks of topic analysis: segmentation and link detection. This method combines the lexical recurrence in texts and the relations from a collocation network to compensate for the respective weaknesses of the two approaches. We report its evaluation for segmentation on a corpus in French and another in English and we propose an evaluation measure that specifically suits that kind of systems.

Read the paper · More papers on PaperTik