All translations

Enter a message name below to show all available translations.

Found 3 translations.

Name	Current message text
^h English (en)	* '''ELMo''' (Peters et al., 2018) — uses a bidirectional {{Term\|long short-term memory\|LSTM}} to generate context-dependent word representations. * '''BERT''' (Devlin et al., 2019) — uses a {{Term\|transformer}} encoder trained with masked language modelling. * '''GPT''' series (Radford et al., 2018–) — uses a {{Term\|transformer}} decoder trained autoregressively.
^h Spanish (es)	* '''ELMo''' (Peters et al., 2018) — utiliza una {{Term\|long short-term memory\|LSTM}} bidireccional para generar representaciones de palabras dependientes del contexto. * '''BERT''' (Devlin et al., 2019) — utiliza un codificador {{Term\|transformer\|transformer}} entrenado con modelado de lenguaje enmascarado. * Serie '''GPT''' (Radford et al., 2018–) — utiliza un decodificador {{Term\|transformer\|transformer}} entrenado de forma autorregresiva.
^h Chinese (zh)	* '''ELMo'''（Peters 等，2018）— 使用双向 {{Term\|long short-term memory\|LSTM}} 生成依赖上下文的词表示。 * '''BERT'''（Devlin 等，2019）— 使用以掩码语言建模训练的 {{Term\|transformer\|Transformer}} 编码器。 * '''GPT''' 系列（Radford 等，2018–）— 使用以自回归方式训练的 {{Term\|transformer\|Transformer}} 解码器。