Guide-yakabatana mibvunzo · Pakati Nhanho

Shoko2Vec Skip-Gram uye CBOW Quiz

Enzanisa Word2Vec's CBOW uye Skip-Gram zvinangwa, zvisina kunaka sampling, akadzidza mavheta, uye sarudzo dzinokanganisa isingawanzo-mazwi kudzidziswa.

Nzira dzekutungamira dzinoenderanaWord2vec Skip Gram Uye Cbow
Mubvunzo 1 ye 8

Chii chinofanotaura Skip-Gram architecture?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinofanotaura Skip-Gram architecture?
    • Mazwi akatenderedza mazwi kubva pakati pezwi
    • Izwi repakati kubva pamazwi akapoteredza
    • Mutsara unotevera mugwaro
    • Chikamu-che-tegi yekutaura yezwi rega rega
  2. Ndeipi chaiyo inobatsira kubuda kwekudzidzisa Word2Vec modhi?
    • Kufembera kwechokwadi pamashoko akapoteredza
    • Iyo yakadzidza huremu matrix, iyo mitsetse iri izwi vectors
    • Muti wakapatsanurwa wemutsara
    • Mukana wekirasi yega yega gwaro
  3. Sei Shoko2Vec richishandisa negative sampling?
    • Kuwedzera saizi yemazwi
    • Kuturikira pakati pemitauro
    • Kuti udzivise inodhura yakazara softmax pamusoro pese mazwi
    • Kubvisa mazwi ekumisa otomatiki
  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. Ndeipi inozivikanwa pfuma yeWord2Vec vectors inoratidzwa ne "mambo - murume + mukadzi ≈ mambokadzi"?
    • Vector analogies kuburikidza nemutsara arithmetic
    • Kunyatso tsvaga muduramazwi
    • Kugadzirisa kukanganisa kwegirama
    • Sentence-length normalization
  6. Ndiani akaunza Word2Vec uye mugore ripi?
    • Geoffrey Hinton kuToronto, 2006
    • Tomas Mikolov nevamwe vaaishanda navo ku Google, 2013
    • Yann LeCun kuBell 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