Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya Tafsiri ya Mashine

Angalia upatanishi wa data ya tafsiri, uwekaji tokeni, vikomo vya BLEU, tathmini ya jozi za lugha na hitilafu za kimaana kama vile nambari zilizobadilishwa au ukanushaji.

Njia za mwongozo zinazohusianaTafsiri ya Mashine
Swali 1 ya 8

Data ya mafunzo sambamba ina nini?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Data ya mafunzo sambamba ina nini?
    • Vipande vya chanzo vilivyopachikwa na tafsiri zinazolingana
    • Nyaraka zisizo na uhusiano zilizopangwa kwa fonti
    • Marejeleo ya lugha lengwa pekee
    • Orodha ya utabiri wa modeli bila vyanzo
  2. Mlingano usio sahihi wa chanzo na lengwa unaweza kufundisha nini modeli ya tafsiri?
    • Uboreshaji wa uhakika katika ufasaha
    • Uhusiano usio sahihi kati ya vipande
    • Tafsiri sahihi kwa kila lugha
    • Marejeleo bora ya BLEU
  3. Kwa nini kuweka nyaraka zinazohusiana pamoja wakati wa kugawanya data ya tathmini?
    • Kuondoa haja ya marejeleo
    • Kufanya tokenization iwe sawa
    • Kupunguza uvujaji wa nakala karibu katika mgawanyiko
    • Kuongeza urefu wa sentensi
  4. Tokenizer hugawanya mfumo mmoja wa uandishi kuwa vitengo vingi zaidi. Mthamini anapaswa kuangalia nini?
    • Iwapo chanzo na lengwa hutumia alfabeti sawa
    • Jina la modeli pekee
    • Whether BLEU is always high
    • Length limits and whether either passage is truncated
  5. What does BLEU compare?
    • Whether a translation is legally valid
    • Patterns of word sequences with reference translations
    • The full meaning and readability of a passage
    • The number of languages in a model
  6. A candidate translation changes “did not arrive” to “did arrive.” What error should reviewers flag?
    • An insertion that cannot matter
    • A casing normalization choice
    • Incorrect negation that reverses meaning
    • A target-language tokenization win
  7. A model has a strong average score across several well-resourced languages. What could that conceal?
    • Poor performance in a less-represented language or specialized domain
    • That all language pairs are equally reliable
    • That there are no terminology errors
    • That the test set has no duplicates
  8. What should accompany an automatic metric in translation evaluation?
    • A single score without settings
    • Only a larger reference corpus
    • An assumption that meaning is preserved
    • A documented setup and bilingual review of specific errors