Concept information
Terme préférentiel
ELMo
Définition
- Type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). (Peters et al., 2018).
Concept générique
Exemple
- We train ELMo on clinical notes and create mention representations m by running the entire sentence through the model and selecting the resulting word representations for the mention (the lowest token representation) from the LSTM. (Schumacher, Mulyar & Dredze, 2020)
Traductions
-
français
URI
http://data.loterre.fr/ark:/67375/8LP-FD8BMCKD-W
{{label}}
{{#each values }} {{! loop through ConceptPropertyValue objects }}
{{#if prefLabel }}
{{/if}}
{{/each}}
{{#if notation }}{{ notation }} {{/if}}{{ prefLabel }}
{{#ifDifferentLabelLang lang }} ({{ lang }}){{/ifDifferentLabelLang}}
{{#if vocabName }}
{{ vocabName }}
{{/if}}