Ikibazo gihuza ibibazo · Hagati Urwego

Ikibazo cyo Kwinjiza Ijambo

Ongera usuzume ijambo wize, ibyerekezo bihagaze hamwe nibisobanuro, isano ya vector, kugereranya cosine, nimbibi zisa.

Inzira zijyanye no kuyoboraIjambo
Ikibazo 1 Bya 8

How does a learned word embedding represent a word for numerical comparison?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. How does a learned word embedding represent a word for numerical comparison?
    • As a plain-text dictionary entry only
    • As a vector of learned numerical features
    • As a complete recorded pronunciation only
    • As a manually assigned grammar rule
  2. Nigute moderi nkijambo2vec yiga icyo ijambo risobanura?
    • Mugusoma intoki zanditswe mubisobanuro
    • Kubara inyuguti muri buri jambo
    • Iyo witegereje andi magambo akunda kugaragara hafi yayo mubwinshi bwinyandiko
    • Mugusaba abatanga amanota yabantu gutsinda ijambo ryose
  3. What does the classic king-minus-man-plus-woman vector example illustrate?
    • Some learned representations capture relationships through vector offsets
    • Every word relation obeys an exact arithmetic law
    • Vector arithmetic verifies every factual statement
    • The vector stores a word's exact spelling only
  4. Ni irihe tandukaniro nyamukuru riri hagati yijambo2vec / GloVe gushiramo no gushiramo imbere muburyo bugezweho bwa transformateur?
    • Abahindura ntibakoresha imibare namba
    • GloVe ikora kumashusho gusa
    • Moderi igezweho ntishobora kwerekana ibisobanuro
    • Ijambo2vec ritanga icyerekezo kimwe gihamye kuri buri jambo, mugihe impinduka zitanga imiterere-ishingiye kumurongo
  5. Ni ikihe gikorwa gishingiye cyane cyane ku kugereranya ibice?
    • Kubara umubare rusange wamagambo murinyandiko
    • Guhindura inyandiko mumutwe muto
    • Gushakisha ibisobanuro bisobanura inyandiko zifite ibisobanuro bisa kubibazo
    • Kugenzura ingano ya dosiye kuri disiki
  6. Which scale of dimensionality is found in common released classic word-vector configurations?
    • Exactly one coordinate for every model
    • Tens or hundreds of learned coordinates per word
    • Exactly two coordinates in all word2vec models
    • At least ten million coordinates per word by definition
  7. In a toy word-vector comparison, what is the cosine similarity of the nonzero vectors one-zero and zero-one?
    • Imwe
    • Minus one
    • Babiri
    • Zeru
  8. What should the first coordinate of an arbitrary learned word embedding be assumed to mean?
    • A learned feature without a universal predetermined linguistic label
    • The word's character count in every model
    • A fixed sentiment score in every dataset
    • The document's factual reliability by definition