Cuestionario vinculado a una guía · Medio Nivel

Prueba de modelos BERT y codificadores

Revise el contexto BERT, el preentrenamiento enmascarado, los codificadores, la adaptación, las representaciones, las variantes eficientes, los objetivos de la siguiente oración y las incrustaciones de entrada.

Rutas de guía relacionadasModelos de Bert y codificador
Pregunta 1 de 8

Which contextual access does bidirectional attention permit in the original BERT encoder input?

Vista previa de cada pregunta8 preguntas

Las respuestas y explicaciones aparecen a medida que realiza el cuestionario.

  1. Which contextual access does bidirectional attention permit in the original BERT encoder input?
    • Information from both left and right within the allowed input
    • Only the previous token in every layer
    • Only a second unrelated language
    • A guarantee of two correct answers to every question
  2. Which original BERT pretraining objective predicts selected token identities using surrounding context?
    • Only next-token prediction under a causal mask
    • Only human-written class labels for complete documents
    • Only a fixed image reconstruction objective
    • Modelado de lenguaje enmascarado
  3. Which transformer component provides the original BERT representation architecture?
    • Only the autoregressive decoder
    • The encoder
    • A recurrent-only sequence network
    • A convolution-only image decoder
  4. What sequence of training stages is illustrated by BERT pretraining followed by downstream fine-tuning?
    • Always train a completely new network from random parameters for every example
    • Apply the task head before creating any learned representation
    • Learn a corpus-based starting representation, then adapt it to a defined task
    • Guarantee that every target task uses no labeled data
  5. What output can the original BERT encoder provide to classification or span-prediction heads?
    • Only a long autoregressive continuation in every task
    • Formas de onda de audio sin procesar
    • Pixel-level image output
    • Contextual text representations
  6. Which comparison accurately distinguishes the parameter-related designs of DistilBERT and ALBERT?
    • DistilBERT uses distillation; ALBERT uses factorized embeddings and cross-layer sharing
    • Both are guarantees of identical speed and accuracy on every task
    • Both replace all text input with image pixels
    • Neither retains any learned encoder representation
  7. Which label distinction is used in the original BERT next-sentence prediction task?
    • A positive versus negative product review
    • A token's verb tense versus noun number
    • An actual next sentence versus a randomly sampled alternative
    • A source sentence's font size versus text color
  8. Which three representations are added in the original BERT input embedding?
    • Only a single corpus-frequency number
    • Token, position, and segment embeddings
    • Decoder probabilities, image pixels, and audio pitch
    • Only one fixed vector shared by every input position