Skip to Main content Skip to Navigation
Conference papers

Détection de phrases comparatives pour le résumé de comparaison grâce à l'apprentissage profond.

Abstract : Comparative summarization seek to compare and contrast important information from two sets of documents dealing with the same topic. This task adds a new understanding’s dimension by analyzing different scenarios at the same time. To generate such a summary, we present a new method for comparative sentence detection using deep learning. Due to the lack of available resources for this task, we built an evaluation corpus. On this corpus, our method shows the best results compared to a set of classical semantic similarity measures
Document type :
Conference papers
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03436422
Contributor : Ccsd Sciencesconf.Org Connect in order to contact the contributor
Submitted on : Friday, November 19, 2021 - 12:25:36 PM
Last modification on : Tuesday, January 11, 2022 - 5:56:23 PM

File

Nyzam_detect_comparative_JIRC_...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03436422, version 1

Citation

Valentin Nyzam. Détection de phrases comparatives pour le résumé de comparaison grâce à l'apprentissage profond.. Journées Informatiques en Région Centre-Val de Loire, Université de Tours, Oct 2021, Blois, France. ⟨hal-03436422⟩

Share

Metrics

Les métriques sont temporairement indisponibles