Concept information
Preferred term
SBERT
Definition
- "a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity." (Reimers & Gurevych, 2019).
Broader concept
Entry terms
- Setence-BERT
Bibliographic citation(s)
- • Reimers, N., & Gurevych, I. (2019). Sentence-BERT : Sentence embeddings using Siamese BERT-networks. arXiv:1908.10084 [cs]. http://arxiv.org/abs/1908.10084
based on
has application field
has design country
- Germany
has for input language
implements
is executed in
In other languages
-
French
URI
http://data.loterre.fr/ark:/67375/LTK-K4JM9GW7-F
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}