Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Luqadda Dabiiciga ah iyo Kacdoonka

Baro ka-hortagga NLI, sumadaha dhexdhexaadka ah, kaydinta xogta, agabka beddelka, iyo xadka hubinta caddaynta.

Wadooyinka haga ee la xidhiidhaKa-soo-jeedinta Luuqadda Dabiiciga ah iyo Dareen-celinta
Su'aal 1 ee 8

Waa maxay saddexda calaamadood ee cabbirka luuqadda dabiiciga ah?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Waa maxay saddexda calaamadood ee cabbirka luuqadda dabiiciga ah?
    • Isku soo wada duuboo, iska hor imaad, dhexdhexaad ah
    • Togan, taban, dhexdhexaad ah
    • Run, been, aan la garanayn
    • Mawduuc, fal, shay
  2. Gudaha NLI, waa maxay macnaha 'ku-xirnaanta'?
    • Labada jumladood wax xidhiidh ah ma laha
    • Mala-awaalku waa inuu ahaadaa mid run ah marka la eego aragtida
    • Mala-awaalku waa inuu noqdaa mid been abuur ah marka la eego aragtida
    • Weedhaha naxwe ahaan waa isku mid
  3. Marka la eego fikradda 'nin ayaa masraxa ku ciyaaraya gitaarka', mala awaalkee ayaa iska hor imaanaya?
    • Qof ayaa qaadaya muusik
    • Dadku waxay jecel yihiin heesta
    • Marxaladu waa faaruq
    • Muusikiiste waxa uu hayaa qalab
  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. Waa kuwee xog-ururinta si weyn loo isticmaalo in lagu tababaro laguna qiimeeyo NLI?
    • SNLI iyo MultiNLI
    • ImageNet iyo CIFAR
    • MNIST iyo SVHN
    • WikiText iyo 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