AWS Certification Exam AI Practitioner (Practice Questions) set16
通常
試験時間: 00:00問題時間: 00:00
問題一覧
問題 29 / 65
Which metric is least suitable for evaluating the naturalness and contextual appropriateness of open-ended conversations?
①BLEU score
②ROUGE score
③Perplexity
④Human subjective evaluation
⑤RMSE