Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Codaynta Byte-Pair

Dib u eeg isku darka BPE, calaamadaha bilawga, daboolida baytariga, asalka isku xidhka, codaynta darajada, qaybo naadir ah, xisaabinta erayada, iyo dejinta UTF-8.

Wadooyinka haga ee la xidhiidhaCodaynta Lammaanaha Byte
Su'aal 1 ee 8

Hawlgalkee calaamada xiga ayaa lagu soo celceliyaa tababarka erayada BPE ee caadiga ah?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Hawlgalkee calaamada xiga ayaa lagu soo celceliyaa tababarka erayada BPE ee caadiga ah?
    • Deleting all low-frequency words from the language
    • Merging a most-frequent pair into a larger symbol
    • Sorting complete documents by title
    • Selecting pairs solely by their alphabetical spelling
  2. Maxay BPE ula dhaqantaa qoraalka sida marka ay bilowdo tababarka?
    • jumlado dhan
    • 8-token blocks go'an
    • Jilayaasha shakhsi ahaaneed ama bytes
    • Weedhaha hore loo turjumay
  3. Qaabaynta heerka-byte ee BPE ee daboolaya dhammaan 256 qiyamka byte-ka saldhiga, sidee loogu matali karaa qoraalka aan la aqoon ee saxda ah ee UTF-8?
    • Through its constituent bytes when larger pieces are unavailable
    • By storing every possible complete word in the finite vocabulary
    • By requiring the input to be translated into English first
    • By assigning every unseen character one shared unknown ID
  4. Halkee bay Algorithm-ka BPE asal ahaan ka timid ka hor inta aysan NLP qaadan?
    • Isku-buufinta sawirka
    • Codaynta codka
    • Tilmaanta database-ka
    • Cadaadiska xogta
  5. Marka GPT-2's encoder-ka BPE ee la daabacay uu helo lammaane badan oo u qalma, maxaa go'aaminaya isku-darka doorashada?
    • A new random vocabulary fit on that one input
    • The text file's creation date
    • The priorities in the learned merge ranks
    • The order of a human-written list of target meanings
  6. What can happen when an unfamiliar word lacks larger learned BPE pieces?
    • It must be replaced by an unrelated synonym
    • It remains represented by several smaller available pieces
    • It necessarily becomes one new learned token during inference
    • It is always silently removed from the input
  7. An illustrative BPE vocabulary has 256 base byte tokens, two distinct added merge tokens, and one separate special token. What is its total size?
    • 256
    • 258
    • 512
    • 259
  8. In GPT-2's published decoder, what is reconstructed before converting the result from UTF-8 into text?
    • The complete byte sequence represented by the token pieces
    • An independent Unicode character from every individual token first
    • A new corpus-frequency table for training merges
    • The model's output-label probabilities