IDEAS home Printed from https://ideas.repec.org/p/hal/journl/hal-05075552.html
   My bibliography  Save this paper

Le traitement automatisé du langage naturel : l’apport des transformers et les enjeux pour les sciences économiques

Author

Listed:
  • Charles Condevaux

    (UNIMES - Nîmes Université)

  • Stéphane Mussard

    (UNIMES - Nîmes Université)

Abstract

Suite à l'abandon progressif des réseaux de neurones récurrents au profit des transformers, la recherche en traitement du langage naturel se concentre depuis 2018 dans la construction de grands modèles de langue. Capables de tenir des conversations ou de résoudre des tâches complexes telles que la génération de résumé et la traduction, l'entraînement de ces architectures suit deux principes : une phase généraliste sur des corpus gigantesques puis une spécialisation sur des problématiques bien définies. Au coeur de ces modèles, le mécanisme d'attention permet le traitement de séquences de natures diverses (texte, audio, valeurs numériques) en connectant les éléments entre eux grâce à des matrices de scores. Cet article expose la méthode, l'architecture et les tâches réalisables par les transformers en sciences économiques.

Suggested Citation

  • Charles Condevaux & Stéphane Mussard, 2025. "Le traitement automatisé du langage naturel : l’apport des transformers et les enjeux pour les sciences économiques," Post-Print hal-05075552, HAL.
    • Handle: RePEc:hal:journl:hal-05075552
    DOI: 10.3917/redp.346.0947
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a search for a similarly titled item that would be available.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:hal:journl:hal-05075552. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: CCSD (email available below). General contact details of provider: https://hal.archives-ouvertes.fr/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.