Maswali yanayounganishwa na mwongozo · Kati Kiwango

Word2Vec Skip-Gram na Maswali ya CBOW

Linganisha CBOW ya Word2Vec na malengo ya Skip-Gram, sampuli hasi, vekta zilizojifunza, na chaguo zinazoathiri mafunzo ya maneno adimu.

Njia za mwongozo zinazohusianaWord2vec Ruka Gram na Cbow
Swali 1 ya 8

Usanifu wa Skip-Gram unatabiri nini?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Usanifu wa Skip-Gram unatabiri nini?
    • Maneno yanayozunguka muktadha kutoka kwa neno la katikati
    • Neno la katikati kutoka kwa maneno ya muktadha unaozunguka
    • Sentensi inayofuata katika hati
    • Lebo ya sehemu ya hotuba ya kila neno
  2. Ni nini matokeo muhimu ya kufunza mfano wa Word2Vec?
    • Usahihi wa utabiri wa maneno ya muktadha
    • Matrix ya uzani iliyojifunza, ambayo safu zake ni vekta za maneno
    • Mti wa kuchanganua wa sentensi
    • Uwezekano wa kila darasa la hati
  3. Kwa nini Word2Vec hutumia sampuli hasi?
    • Kuongeza saizi ya msamiati
    • Ili kutafsiri kati ya lugha
    • Ili kuzuia laini kamili ya gharama kubwa juu ya msamiati mzima
    • Kuondoa maneno ya kuacha moja kwa moja
  4. What does subsampling frequent words do in the later Word2Vec training method?
    • It reduces the influence of very frequent words and can speed training
    • It turns every word into a character n-gram
    • It changes CBOW into a sentence classifier
    • It guarantees better vectors for every rare word
  5. Ni mali gani maarufu ya vekta za Word2Vec inayoonyeshwa na "mfalme - mwanamume + mwanamke ≈ malkia"?
    • Milinganisho ya vekta kupitia hesabu ya mstari
    • Utafutaji kamili wa kamusi
    • Marekebisho ya makosa ya kisarufi
    • Urekebishaji wa urefu wa sentensi
  6. Nani alianzisha Word2Vec na mwaka gani?
    • Geoffrey Hinton huko Toronto, 2006
    • Tomas Mikolov na wenzake katika Google, 2013
    • Yann LeCun katika Bell Labs, 1998
    • OpenAI, 2018
  7. What does the CBOW architecture predict from its input context?
    • Each future paragraph in the document
    • The sentiment label of the full corpus
    • The center word surrounded by the context window
    • The spelling of a character n-gram
  8. What distribution does the original Word2Vec paper use to draw negative samples?
    • A uniform distribution over all character n-grams
    • A distribution based only on word length
    • A distribution proportional to squared inverse frequency
    • A unigram word-frequency distribution raised to the 0.75 power