Quiz buy wane làkk wiñ nàmp

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy ñatti etiket yiñ miin ci wàllu làkk wiñ nàmp?
   • Entailment, werante, amul benn boor
   • Positif, négatif, neutre
   • Dëgg, fen, xamu ñu
   • Sujet, verb, objet
2. Ci NLI, luy 'jëfandikoo'?
   • Ñaari tegtal yi bokku ñu
   • Hypothèse bi dafa wara dëgg ndax premise bi
   • Hypothèse bi dafa wara nekk njuumte ndax premise bi
   • Frase yi dañuy nuru ci wàllu nàfar
3. Buñu sukkandikoo ci premise bii di 'Ku góor kuy jouer gitaar ci kaw seen bi,' ban hypothèse mooy réer?
   • Nit mingi jouer music
   • Seetaankat yi bëgg nañu way wi
   • Seen bi amul kenn
   • Waykat bi yor ab jumtukaay
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. Yan done lañu gëna jëfandikoo ngir tàggat ak jàngat NLI?
   • SNLI ak NLI yu bari
   • Nataal net ak CIFAR
   • MNIST ak SVHN
   • WikiText ak 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