1{2 "document_id": "lb_qasper_57de270868df43af983000c70076588676aaf9bfb5fbfca5",3 "family": "public_qasper",4 "split": "test",5 "document_hash": "09a8bd3684c0edf68c736659576022a5bace0c893bc0705384a039a0cf7f53b4",6 "questions": [7 {8 "question_id": "q00",9 "qtype": "qasper",10 "question": "Which baselines are used for evaluation?",11 "answer": "Pointer-Gen, Pointer-Gen+Pos, Pointer-Gen+Same-FT, Pointer-Gen+Pos-FT, Pointer-Gen+RL-ROUGE, Pointer-Gen+RL-SEN",12 "aliases": [],13 "answer_type": "qa_f1",14 "tolerance": 0.0,15 "supporting_fact_ids": [],16 "answer_position_frac": -1.017 }18 ],19 "facts": []20}