Guide-yakabatana mibvunzo · Zvakaoma Nhanho

XLNet Permutation Modelling Quiz

Inotarisa permutation factorization, mbiri-yerukova kutarisisa, Transformer-XL kudzokorora, uye kuti zvikumbiro zvebhenji zvinoenderana sei nemasetirwo akafanana.

Nzira dzekutungamira dzinoenderanaXlnet Permutation Modelling
Mubvunzo 1 ye 8

Ndechipi chinangwa chepretraining chinoshandiswa neXLNet?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndechipi chinangwa chepretraining chinoshandiswa neXLNet?
    • Permutation mutauro wokuenzanisira
    • Masked language modelling
    • Yakatsiviwa chiratidzo chekuonekwa
    • Kufanotaura kwemutsara unotevera
  2. Ndeipi kushaya simba kweBERT yaive XLNet yakagadzirirwa kugadzirisa?
    • BERT yaive idiki zvakanyanya
    • Chiratidzo che [MASK] chinokonzera pretrain/fine-tune kusapindirana uye chinotora masked-chiratidzo kuzvimiririra.
    • BERT yaisakwanisa kubata mitsara mipfupi
    • BERT yakashaya maencodings enzvimbo
  3. Chii chinonzi XLNet's two-stream self-attention inoparadzanisa?
    • Encoder uye decoder layer
    • Kudzidzira uye inference magirafu
    • A content stream uye query stream
    • Token uye mitsara inomisikidzwa
  4. Ko XLNet inokwenya mazwi mumutsara here?
    • Ehe, inodzokorodza zvisina tsarukano iwo chaiwo tokens
    • Hongu, asi chete panguva yekugadzirisa zvakanaka
    • Kwete, haimbochinji chero kuodha zvachose
    • Kwete, inobvumidza iyo factorization odha uchishandisa yekutarisisa masks uchichengeta zvinzvimbo
  5. Ndechipi chivakwa chinoshanda se XLNet musana wemamiriro enguva refu?
    • Transformer-XL
    • LSTM
    • Chekutanga vanilla Transformer
    • Convolutional network
  6. How does XLNet combine bidirectional context with autoregressive prediction?
    • It predicts all tokens independently with no attention mask
    • It predicts in sampled factorization orders without inserting a [MASK] input token, using attention masks
    • It physically shuffles the sentence before every prediction
    • It replaces autoregressive prediction with a denoising autoencoder
  7. For a token sequence A B C, suppose a sampled factorization order predicts C before A and B. What context is available when predicting C?
    • The tokens A and B must always be provided first
    • Only the next sentence is available
    • No earlier tokens in that sampled order, although C remains at its original input position
    • The input sequence is physically reordered to C A B
  8. How does XLNet prevent the target token from leaking into its own prediction query?
    • It removes the target from the entire training sequence
    • It uses the target’s label as an input embedding
    • It replaces the token with a [MASK] symbol
    • The query stream represents the target position without its token content