Quiz buy dugal ay baat

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

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. naka la model yu melni word2vec di jàngee lu baat bi di tekki?
   • Sooy jàng liñu bind ak loxo ci diksoneer
   • Ni ñuy lim araf yi ci baat bu nekk
   • Soo xoolee ban yeneen baat ñoo ko gëna jege ci mbind yu bari
   • Soo laajee nit ñi ñu joxe poñ ci baat bu nekk
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. Lan mooy wuute bu mag bi am ci digganté word2vec/GloVe ak li nekk ci biir model transformateur yu bees yi?
   • Transformatër yi duñu jëfandikoo benn nimero
   • GloVe ci nataal yi kese lay dox
   • Royuwaayi jamono jii mënuñu joxe luñuy tekki
   • Word2vec dafay joxe benn vecteur fixe ci baat bu nekk, fekk transformateur yi dañuy defar vecteur yu aju ci contexte
5. Ban liggéey moo gëna aju ci méngale vecteur yuñ samp?
   • Lim limu baat yi ci benn këyit
   • Soppi mbind ci arafu mag
   • Seetug semantik buy gis këyit yu am luñuy tekki luy nuru ab laaj
   • Saytu dayo fichier bi ci disk bi
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?
   • Benn
   • Minus one
   • Ñaar
   • Zéro
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