Abstract : This paper presents a model based on LSA which attempts to simulate the way humans assess student summaries. It is based on the automatic detection of 5 cognitive operations that student may use in writing a summary. Comparisons with dataand the construction of a new proposition denoting a global from 33 human raters show the strengths and limits of this approach.
https://hal.archives-ouvertes.fr/hal-00323325
Contributeur : Philippe Dessus <>
Soumis le : samedi 20 septembre 2008 - 10:37:35 Dernière modification le : vendredi 20 novembre 2020 - 14:54:16 Archivage à long terme le : : vendredi 4 juin 2010 - 11:38:05
Sonia Mandin, Benoît Lemaire, Philippe Dessus. Modeling summarization assessment strategies with LSA. First European Workshop on Latent Semantic Analysis in Technology Enhanced Learning, Mar 2007, Heerlen, Netherlands. pp.20-21. ⟨hal-00323325⟩