{
  "lesson": "11-machine-translation",
  "title": "Machine Translation",
  "questions": [
    {
      "stage": "pre",
      "question": "What does BLEU measure?",
      "options": [
        "N-gram precision (typically 1-4) between hypothesis and reference, with a brevity penalty",
        "Embedding cosine similarity",
        "Language identification accuracy",
        "Character-level F-score"
      ],
      "correct": 0,
      "explanation": "BLEU is the geometric mean of 1-4-gram precision against references, plus a brevity penalty."
    },
    {
      "stage": "pre",
      "question": "Why use sacrebleu instead of rolling your own BLEU?",
      "options": [
        "It runs on GPU",
        "It is more accurate",
        "It normalizes tokenization so scores are comparable across papers and runs",
        "It supports streaming"
      ],
      "correct": 2,
      "explanation": "sacrebleu freezes tokenization, removing a common source of incomparable BLEU numbers."
    },
    {
      "stage": "check",
      "question": "Which NLLB-specific setting controls the target language during decoding?",
      "options": [
        "src_lang",
        "forced_bos_token_id set to the target language code's token id",
        "num_beams",
        "length_penalty"
      ],
      "correct": 1,
      "explanation": "NLLB forces the first decoded token to a target-language code via forced_bos_token_id."
    },
    {
      "stage": "check",
      "question": "Which metric family is the 2026 default for production MT quality where labeled data exists?",
      "options": [
        "Token edit distance",
        "Latency",
        "BLEU alone",
        "Learned metrics such as COMET (and BERTScore/BLEURT) trained on human judgment"
      ],
      "correct": 3,
      "explanation": "Learned metrics like COMET correlate more strongly with human judgment than BLEU/chrF alone."
    },
    {
      "stage": "check",
      "question": "When does chrF tend to be more informative than BLEU?",
      "options": [
        "For morphologically rich languages where character-level matches catch inflectional variants BLEU misses",
        "When using beam search",
        "On very short sentences",
        "Whenever a reference exists"
      ],
      "correct": 0,
      "explanation": "Character F-score captures partial morphological matches that word-level BLEU undercounts."
    },
    {
      "stage": "post",
      "question": "What is off-target generation in multilingual MT?",
      "options": [
        "Output that drops named entities",
        "The model decodes into the wrong target language (e.g. NLLB outputting Spanish when French was requested)",
        "Output that is too short",
        "Output that misses punctuation"
      ],
      "correct": 1,
      "explanation": "Off-target generation is common on rare language pairs; a post-translation language-ID check catches it."
    },
    {
      "stage": "post",
      "question": "Why does fine-tuning on a few thousand high-quality domain pairs often beat much larger noisy web data?",
      "options": [
        "Quality and domain match dominate volume; noisy parallel data introduces drift and hallucination",
        "Smaller datasets train faster",
        "Web data is illegal to use",
        "Larger data overflows GPU memory"
      ],
      "correct": 0,
      "explanation": "Clean domain-aligned pairs are the largest production lever; noisy data degrades adaptation."
    },
    {
      "stage": "post",
      "question": "When is an LLM (e.g. GPT-4) likely to outperform a specialized MT model in 2026?",
      "options": [
        "Latency-critical browser translation",
        "Idiomatic content, long context, stylistic adaptation via prompting, or content requiring tone control",
        "Highest throughput batch translation",
        "Small-language pairs with millions of parallel sentences"
      ],
      "correct": 1,
      "explanation": "LLMs win on idiomatic, long-context, or style-controlled translation; specialized MT wins on throughput and latency."
    }
  ]
}