Passer au contenu principal

Vocabulary of natural language processing

Choisissez le vocabulaire dans lequel chercher

  • Aide
aligner
annoter
télécharger

Concept information

... > NLP methods and tools > model > statistical model > foundation model > language model > ALUM
... > NLP methods and tools > statistics > statistical model > foundation model > language model > ALUM

Terme préférentiel

ALUM  

Définition

  • Language model which regularizes the training objective by applying perturbations in the embedding space that maximizes the adversarial loss (Liu et al., 2020).

Concept générique

Synonyme(s)

  • Adversarial training for large neural LangUage Models

Contexte(s) définitoire(s)

  • ALUM (Liu et al. 2020) is the state-of-theart adversarial training method for neural language models which regularizes fine-tuning via perturbations in the embedding space. (Chen, Shen, Chen & Yang, 2021)

Exemple

  • Both ALUM and InfoBERT take RoBERTa-large as the backbone model. (Chen, Zhang & Zhao, 2022)

Traductions

URI

http://data.loterre.fr/ark:/67375/8LP-FZWTVBWP-M

Télécharger ce concept :

RDF/XML TURTLE JSON-LD Dernière modification le 26/04/2024