引導式測驗 · 中等 等級

自然語言推理與蘊涵測驗

了解 NLI 的蘊含、矛盾和中性標籤、基準資料集、變壓器輸入和證據檢查限制。

相關引導路徑自然語言推理與蘊涵
問題 1 的 8

自然語言推理的三個標準標籤是什麼?

預覽每個問題8 問題

當您參加測驗時,就會出現答案和解釋。

  1. 自然語言推理的三個標準標籤是什麼?
    • 蘊含、矛盾、中性
    • 正、負、中性
    • 真、假、未知
    • 主詞、動詞、受詞
  2. 在 NLI 中,「蘊含」是什麼意思?
    • 兩句話無關
    • 給定前提,假設必須為真
    • 給定前提,假設一定是錯的
    • 這些句子在文法上是相同的
  3. 給定前提“一個人在舞台上彈吉他”,哪個假設是矛盾的?
    • 一個人在演奏音樂
    • 群眾都喜歡這首歌
    • 舞台空無一人
    • 音樂家拿著樂器
  4. NLI 資料集中的標註人工痕跡是什麼?
    • A model that reasons perfectly with very little data
    • A dataset where every annotator agrees
    • A premise that is always longer than its hypothesis
    • A spurious cue that lets a model guess labels without reasoning about the premise-hypothesis relation
  5. 哪些資料集被廣泛用於訓練和評估 NLI?
    • SNLI 和 MultiNLI
    • ImageNet 與 CIFAR
    • MNIST 和 SVHN
    • 維基文本和 Penn Treebank
  6. How can NLI support a check of a generated claim against source evidence?
    • Measure the generated claim’s length
    • Classify whether the evidence entails, contradicts, or leaves the claim neutral
    • Count unique words only
    • Translate the claim into another language
  7. In NLI, what does the neutral label mean?
    • The hypothesis is guaranteed true
    • The hypothesis is guaranteed false
    • The premise neither entails nor contradicts the hypothesis
    • The two sentences are grammatically identical
  8. How does a common transformer NLI classifier present a sentence pair to the model?
    • Encode only the hypothesis and discard the premise
    • Convert both sentences into audio first
    • Train a separate model for every word
    • Concatenate the premise and hypothesis with a separator token