Analyse automatique FrameNet : une étude sur un corpus français de textes encyclopédiques

Abstract : This article presents an automatic frame analysis system evaluated on a corpus of French encyclopedic history texts annotated according to the FrameNet formalism. The chosen approach relies on an integrated sequence labeling model which jointly optimizes frame identification and semantic role segmentation and identification. The purpose of this study is to analyze the task complexity from several dimensions. Hence we provide detailed evaluations from a feature selection point of view and from the data point of view.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01959260
Contributor : Gabriel Marzinotto <>
Submitted on : Tuesday, December 18, 2018 - 3:43:35 PM
Last modification on : Monday, March 4, 2019 - 2:04:14 PM
Document(s) archivé(s) le : Wednesday, March 20, 2019 - 10:45:16 AM

Files

analyse-automatique-framenet(2...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01959260, version 1
  • ARXIV : 1812.08044

Collections

Citation

Gabriel Marzinotto, Géraldine Damnati, Frederic Bechet. Analyse automatique FrameNet : une étude sur un corpus français de textes encyclopédiques. TALN 2017, 2017, Orléans, France. ⟨hal-01959260⟩

Share

Metrics

Record views

43

Files downloads

13