Quiz jàng booy saytu sa bopp

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

1. Where does the supervision signal in the described self-supervised examples come from?
   • A requirement for no training objective
   • Only new human semantic labels for every pretraining example
   • A rule that examples contain no useful information
   • The data and defined transformations of it
2. Which input positions contribute prediction targets to the original BERT masked-language-model loss?
   • The positions selected for the MLM prediction task
   • Every position in the entire input regardless of selection
   • Only the first position of each new sentence
   • Only positions that appear after the final sentence boundary
3. Ci jàngat bu wuute bu melni SimCLR, 'ñaar bu baax' mooy:
   • Ñaari nataal yu amul benn lëkkaloo
   • Ñaari etiket yu nit bind
   • Ñaari gis-gis yuñ yokk ci benn nataal bi wara jege ci bayaali samp gi
   • Ñaari kopi ci done yi
4. What annotation requirement can self-supervised pretraining reduce in the described examples?
   • The need for any usable input data
   • Separate task-specific semantic labels for every pretraining example
   • All computational cost by definition
   • The need to assess downstream performance
5. How can a representation learned through self-supervision be used for a later task?
   • By evaluating a task head or adapting the representation through fine-tuning
   • By assuming every target task requires no labels or validation
   • By discarding all representations before making predictions
   • By treating the pretraining loss as proof of every application's accuracy
6. Lan moo wuutale liggéey bi nit ñi di saytu seen bopp ci xeetu GPT ak liggéeyu BERT?
   • Jëfandikuwul benn mbind
   • Dafay laaj etiketu loxo ngir baat bu nekk
   • Dafay wax luy waaja am ci baat bi njëkk ci benn këyit
   • Dafay wax luy waaja am ci jeton bi ci topp moo gën feesal jeton yu maske
7. In the original SimCLR framework, which component is discarded for the reported downstream representation use?
   • The encoder representation itself
   • The contrastive projection head
   • All training inputs before pretraining begins
   • The positive-pair source-image relationship
8. When original BERT pretraining replaces a selected input position with a random token, what remains its loss target?
   • The newly inserted random token
   • The next sentence's first token in every case
   • The original token before replacement
   • No target, because every random replacement is omitted from training