1{2 "document_id": "lb_qasper_7e2663bb13493e18205f6aab469fee8b2a9df281a0ba0e2a",3 "family": "public_qasper",4 "split": "dev",5 "document_hash": "26f13986c049c772e91731349bf8b554c0074e633bec40f9fc595d3561fb9b60",6 "questions": [7 {8 "question_id": "q00",9 "qtype": "qasper",10 "question": "How do they combine audio and text sequences in their RNN?",11 "answer": "combines the information from these sources using a feed-forward neural model",12 "aliases": [13 "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"14 ],15 "answer_type": "qa_f1",16 "tolerance": 0.0,17 "supporting_fact_ids": [],18 "answer_position_frac": -1.019 }20 ],21 "facts": []22}