{
  "document_id": "lb_qasper_7e2663bb13493e18205f6aab469fee8b2a9df281a0ba0e2a",
  "family": "public_qasper",
  "split": "dev",
  "document_hash": "26f13986c049c772e91731349bf8b554c0074e633bec40f9fc595d3561fb9b60",
  "questions": [
    {
      "question_id": "q00",
      "qtype": "qasper",
      "question": "How do they combine audio and text sequences in their RNN?",
      "answer": "combines the information from these sources using a feed-forward neural model",
      "aliases": [
        "encodes the information from audio and text sequences using dual RNNs and then combines the information from these sources using a feed-forward neural model"
      ],
      "answer_type": "qa_f1",
      "tolerance": 0.0,
      "supporting_fact_ids": [],
      "answer_position_frac": -1.0
    }
  ],
  "facts": []
}