{"id":"W4287891193","doi":"10.18653/v1/2022.wordplay-1.4","title":"A Sequence Modelling Approach to Question Answering in Text-Based Games","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Question answering; Computer science; Transformer; Reinforcement learning; Artificial intelligence; Machine learning; Benchmark (surveying); Language model; Task (project management); Natural language processing","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004598416,0.00008333355,0.00008409071,0.0002041859,0.0001546365,0.00006795308,0.0006945529,0.00001536182,0.0000131408],"category_scores_gemma":[0.00001950981,0.00009067946,0.00002265893,0.0008405697,0.000008925999,0.0001369102,0.0002553748,0.0002359724,0.00001824919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001456596,"about_ca_system_score_gemma":0.00005953374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00243915,"about_ca_topic_score_gemma":0.00001074945,"domain_scores_codex":[0.9988994,0.0001091788,0.0001526251,0.0004127008,0.0002326138,0.0001935098],"domain_scores_gemma":[0.9994068,0.00005654996,0.00003412784,0.0004204012,0.00002037775,0.00006175202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002204188,0.00005748651,0.0009613836,0.000003892199,5.887701e-7,7.914561e-7,0.0003824349,0.9353591,0.0006274399,0.05629758,0.000009858541,0.006297248],"study_design_scores_gemma":[0.00009792855,0.00002979781,0.001466047,0.000004213317,5.227496e-7,0.000003490025,0.00003034233,0.9968131,0.0001108841,0.0008150926,0.0005133383,0.0001152828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07208377,0.000008842902,0.9222597,0.001474896,0.00002654912,0.0002294239,9.498356e-7,0.000264572,0.00365123],"genre_scores_gemma":[0.6163695,1.497065e-7,0.3829679,0.0003530925,0.000005741573,0.0002454785,0.000002626216,0.000005056341,0.00005046288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5442857,"threshold_uncertainty_score":0.3697801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03687691377713465,"score_gpt":0.2905471630438144,"score_spread":0.2536702492666797,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}