Concept information
Terme préférentiel
ERNIE
Définition
- A pre-trained language model on large-scale textual corpora and knowledge graphs. (Loterre)
Concept générique
Exemple
- It shows that ERNIE has a prominent advantage over BERT in both detection and correction. (Zhang, Pang, Zhang, Wang, He, Sun, Wu & Wang, 2021)
- Since ERNIE is not significantly improved compared to BERT in order to reduce model parameters we choose to use BERT as the pre-trained model. (Tan, Hu & Qiu, 2023)
Traductions
-
français
URI
http://data.loterre.fr/ark:/67375/8LP-CF4R9CVM-J
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}