Word2Vec Jaar-Gram ak Laajte CBOW

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan la architecture Skip-Gram wax luy waaja am?
   • Baatu contexte yi ko wër, joge ci baat bi ci digg bi
   • Baatu digg bi ci baat yi ko wër
   • Phrase bi ci topp ci biir benn këyit
   • Etiketu pàccu kàddu bu baat bu nekk
2. Lan mooy njariñu tàggat xeetu Word2Vec?
   • Xalaatal bu jaar yoon ci kàddu yi ci nekk
   • matrix poid biñ jàng, liiñ yi nekk vecteur yu baat yi
   • Garab parse bu tegtal bi
   • Probabilite ngir bépp xeetu këyit
3. Lu tax Word2Vec di jëfandikoo misaal bu baaxul?
   • Yokk vocabulaire bi
   • Tekki ci diggante làkk yi
   • Ngir moytu softmax bu seer bi ci vocabulaire bi yépp
   • Ngir dindi ci saasi baat yiy taxawal
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. Ban màndarga bu siiw ci vecteur Word2Vec lañuy wane ci "buur - góor + jigéen ≈ reine"?
   • analogie vecteur jaaraleko ci arithmétique ligneaire
   • Seetug diksoneer bi
   • Juumtu njuumte ci nàfar
   • Normalisation de longueur de frase
6. Kan moo dugal Word2Vec ak ci ban at?
   • Geoffrey hinton ci toronto, 2006
   • Tomas Mikolov ak ay naataango ci 2013
   • Yann Lecun ci Bell Labs, 1998
   • AIU_AAR_10__, 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