Guide-yakabatana mibvunzo · Pakati Nhanho

FastText Subword Embeddings Quiz

Ongorora FastText's character n-grams, hashed feature buckets, out-of-vocabulary support, morphology, uye kukurumidza kutariswa zvinyorwa.

Nzira dzekutungamira dzinoenderanaFasttext Subword Embeddings
Mubvunzo 1 ye 8

FastText inomiririra sei izwi rimwe chete?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. FastText inomiririra sei izwi rimwe chete?
    • Sebhegi rehunhu n-magiramu akapfupikiswa pamwechete
    • Sechiratidzo chimwe chete chisingaonekwe
    • Setsanangudzo yaro kubva muduramazwi
    • Sechinhu chisina kurongeka vector
  2. Ndeipi mipimo mikuru yeWord2Vec neGloVe inokunda FastText?
    • Vanomhanya zvakanyanya
    • Havagone kugadzira mavheji emazwi asiri emazwi
    • Vanofuratira nyora dzomutauro
    • Vanongoshanda muchirungu chete
  3. Kune izwi rekuti "kupi" rine mavara matatu-n-magiramu, inova n-giramu inoshanda (ine maborder markers)?
    • <kupi>chete
    • xyz
    • whe
    • the
  4. Ndechipi chiri pasi pechinangwa chekudzidzisa icho FastText yekumisikidza modhi inovaka pairi?
    • GloVe matrix factorization
    • Kushandura kwechikamu chechirevo
    • Kurasika kwechikamu chemufananidzo
    • Skip-Gram ine negative sampling
  5. Nei FastText ichinyanya kubatsira kumitauro yakaita seFinnish kana Turkish?
    • Ivo vane morphologically vakapfuma neakawanda emazwi akachinjika anogovana mazwi madiki
    • Vane mazwi mashoma
    • Havashandisi nzvimbo
    • Havana mazwi mashoma
  6. Which separate method did Sennrich and colleagues describe for representing rare words in neural machine translation?
    • Byte-pair encoding as subword units
    • FastText’s hashed character n-gram bucket table
    • A full-word-only vocabulary that discards rare tokens
    • GloVe’s global co-occurrence matrix
  7. How does FastText store learnable features for its character n-grams?
    • It stores every complete sentence as a separate vector
    • It assigns each n-gram a pixel grid in a convolutional decoder
    • It hashes n-grams into a fixed-size bucket table with learned vectors
    • It replaces all subword features with a hand-written dictionary
  8. What can fastText's supervised mode do efficiently with its bag-of-features model?
    • Estimate the 3D shape of an object from a single image
    • Generate new audio waveforms from a spectrogram
    • Compute a global word-word co-occurrence matrix only
    • Classify text for tasks such as language identification or tagging