Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Maelekezo ya Lugha Asilia na Maswali

Jifunze umuhimu wa NLI, ukinzani, na lebo zisizoegemea upande wowote, seti za data za benchmark, pembejeo za transfoma na vikomo vya kukagua ushahidi.

Njia za mwongozo zinazohusianaMaelekezo ya Lugha ya Asili na Maagizo
Swali 1 ya 8

Je, ni lebo gani tatu za kawaida katika makisio ya lugha asilia?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Je, ni lebo gani tatu za kawaida katika makisio ya lugha asilia?
    • Kuingizwa, kupingana, kutokuwa na upande
    • Chanya, hasi, neutral
    • Kweli, uongo, haijulikani
    • Kiima, kitenzi, kitu
  2. Katika NLI, 'ujumuishi' unamaanisha nini?
    • Sentensi hizo mbili hazina uhusiano
    • Dhana ni lazima iwe kweli kutokana na msingi
    • Hypothesis lazima iwe ya uwongo kwa kuzingatia msingi
    • Sentensi zinafanana kisarufi
  3. Kwa kuzingatia dhana ya 'Mwanaume anacheza gitaa jukwaani,' ni nadharia gani inayopingana?
    • Mtu anafanya muziki
    • Umati unapenda wimbo
    • Jukwaa ni tupu
    • Mwanamuziki ameshika ala
  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. Je, ni hifadhidata zipi zinazotumiwa sana kutoa mafunzo na kutathmini NLI?
    • SNLI na MultiNLI
    • ImageNet 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