Ikibazo gihuza ibibazo · Hagati Urwego

Ururimi Kamere Yerekana Ikibazo

Wige ibyifuzo bya NLI, kwivuguruza, hamwe na labels zidafite aho zibogamiye, ibipimo fatizo byerekana imibare, inyongeramusaruro, hamwe nimbibi zo kugenzura ibimenyetso.

Inzira zijyanye no kuyoboraIndimi Kamere Indanganturo
Ikibazo 1 Bya 8

Nibihe birango bitatu bisanzwe mubisobanuro byururimi karemano?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nibihe birango bitatu bisanzwe mubisobanuro byururimi karemano?
    • Kwinjira, kwivuguruza, kutabogama
    • Ibyiza, bibi, bitabogamye
    • Nukuri, ibinyoma, ntibizwi
    • Ingingo, inshinga, ikintu
  2. Muri NLI, 'entailment' bisobanura iki?
    • Interuro zombi ntaho zihuriye
    • Hypothesis igomba kuba impamo ukurikije ishingiro
    • Hypothesis igomba kuba ibinyoma ukurikije ishingiro
    • Interuro zirasa mu kibonezamvugo
  3. Urebye mbere yuko 'Umugabo acuranga gitari kuri stage,' niyihe hypothesis ivuguruzanya?
    • Umuntu arimo akora umuziki
    • Imbaga y'abantu ikunda indirimbo
    • Icyiciro kirimo ubusa
    • Umucuranzi afite igikoresho
  4. What is an annotation artifact in an NLI dataset?
    • 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. Ni izihe mibare zikoreshwa cyane mu guhugura no gusuzuma NLI?
    • SNLI na MultiNLI
    • IshushoNet na CIFAR
    • MNIST na SVHN
    • WikiText na 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