양방향 순환 네트워크 퀴즈

퀴즈를 풀면 정답과 설명이 나타납니다.

1. What does a bidirectional RNN do with an input sequence?
   • Processes only the first half forward
   • Processes it in forward and backward directions and combines the contextual states
   • Uses future tokens as training labels
   • Runs the same hidden state twice in the same direction
2. Why can context from both directions help label a word such as “bank”?
   • Words before and after it can clarify the intended meaning
   • The word has only one possible meaning
   • The model needs no surrounding text
   • The label is stored in the sequence position
3. How are the two directional hidden states commonly combined at a position?
   • Average all positions in the sequence first
   • Discard the backward state
   • Use only the final forward state for every position
   • Concatenate them or otherwise combine them for the output
4. Why can a bidirectional RNN be unsuitable for streaming generation?
   • It cannot process tokens in order
   • It requires class labels at inference
   • It needs future sequence context that is not yet available
   • 이미지에서만 작동합니다.
5. What is one advantage of offline sequence labeling with bidirectionality?
   • Each position can use context on both sides
   • The model needs no sequence boundaries
   • It removes the need for recurrent parameters
   • It guarantees correct token labels
6. Do forward and backward passes share the same recurrent parameters in the guide’s described architecture?
   • Yes, by definition every bidirectional RNN shares weights
   • No; it uses separate recurrent layers for the two directions
   • Only when the sequence has even length
   • They have no parameters
7. Which task is a natural fit when the entire sequence is available?
   • Left-to-right text generation before later tokens exist
   • Live word prediction with zero lookahead
   • Part-of-speech tagging or named-entity recognition
   • Predicting the next unseen sensor reading in a stream
8. What does bidirectional context not guarantee?
   • Access to following input tokens in offline use
   • A combined representation at each position
   • Two traversal directions
   • That the model will correctly interpret every token