Idanwo ti o sopọ mọ itọsọna · Lile Ipele

Kere Bayes Ewu Iyipada adanwo

Tests expected utility, sampled pseudo-references, quadratic candidate comparisons, metric limits, and the candidate-pool constraints of MBR decoding.

Jẹmọ itọsọna awọn ọnaIyipada Ewu Bayes Kere
Ibeere 1 ti 8

Kini iyipada MBR ṣe yan dipo ẹyọkan ti o ṣeeṣe julọ ọkọọkan?

Awotẹlẹ gbogbo ibeere8 ibeere

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

  1. Kini iyipada MBR ṣe yan dipo ẹyọkan ti o ṣeeṣe julọ ọkọọkan?
    • Oludije pẹlu ohun elo ireti ti o ga julọ lodi si awọn abajade miiran ti o ṣeeṣe
    • Awọn kuru ọkọọkan
    • Ayẹwo laileto
    • Awọn gunjulo ọkọọkan
  2. Niwọn bi awọn itọkasi otitọ ko si, kini MBR lo bi awọn itọka afarape?
    • A ti o wa titi ita koposi
    • Awọn pool ti apere tani o wu ara wọn
    • Awọn asọye eniyan
    • Eto ikẹkọ
  3. Kini idi ti MBR ti ko ni iṣiro jẹ gbowolori?
    • O nilo atunṣe awoṣe
    • O nilo kan ti o tobi fokabulari
    • Ifiwera meji ti awọn oludije N jẹ awọn ipe metiriki O(N squared).
    • O nlo ko si GPU
  4. What has COMET been used for in minimum Bayes risk machine-translation experiments?
    • As a universal guarantee of better translation quality
    • As a tokenizer for the candidate pool
    • As an exact reference translation available at inference
    • As a learned utility metric in evaluated translation settings
  5. Iduroṣinṣin ti ara ẹni ni ero ni ibatan si MBR nitori pe:
    • Ṣe ayẹwo ọpọlọpọ awọn ẹwọn ati mu idahun ti o gba julọ julọ
    • Nigbagbogbo gba idahun ti a ṣe ayẹwo akọkọ
    • Nlo wiwa tan ina inu
    • Fojusi pinpin awoṣe
  6. How is risk generally expressed in minimum Bayes risk decision-making?
    • Always one minus a normalized similarity score
    • Expected loss under a chosen loss function and reference distribution
    • The model’s parameter count divided by accuracy
    • The number of candidates sampled
  7. If the chosen utility metric disagrees with human judgments, what will MBR primarily optimize?
    • Human preference automatically overrides the metric
    • The model’s raw next-token likelihood
    • The expected utility under that selected metric
    • The shortest candidate in the pool
  8. If a high-quality answer is missing from the sampled candidate pool, what can MBR do?
    • It guarantees the missing answer is generated
    • It changes the model weights to add the answer
    • It replaces the utility metric with a human reference
    • It can only select or rerank candidates that are in the pool