Idanwo Awọn ifibọ Ọrọ

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

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. Bawo ni awọn awoṣe bii word2vec ṣe kọ kini ọrọ tumọ si?
   • Nipa kika awọn itumọ ti a fi ọwọ kọ lati inu iwe-itumọ
   • Nipa kika awọn lẹta ni ọrọ kọọkan
   • Nipa wíwo eyi ti awọn ọrọ miiran ṣọ lati han nitosi rẹ ni titobi pupọ ti ọrọ
   • Nipa bibeere awọn oṣuwọn eniyan lati ṣe Dimegilio gbogbo ọrọ
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. Kini iyatọ akọkọ laarin awọn ifibọ word2vec/GloVe ati awọn ifisinu inu awọn awoṣe transformer ode oni?
   • Ayirapada lo ko si awọn nọmba ni gbogbo
   • GloVe ṣiṣẹ lori awọn aworan nikan
   • Awọn awoṣe ode oni ko le ṣe aṣoju itumọ
   • Word2vec n funni ni fekito ti o wa titi kan fun ọrọ kan, lakoko ti awọn oluyipada ṣe agbejade awọn adaṣe ti o gbẹkẹle ọrọ-ọrọ
5. Iṣẹ-ṣiṣe wo ni o dale taara taara lori ifiwera awọn ifisinu ifisinu?
   • Kika lapapọ nọmba ti awọn ọrọ ninu iwe kan
   • N yi ọrọ pada si ọrọ nla
   • Iwadi atunmọ ti o wa awọn iwe aṣẹ pẹlu itumọ kanna si ibeere kan
   • Ṣiṣayẹwo iwọn faili kan lori 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?
   • Ọkan
   • Minus one
   • Meji
   • Odo
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