{"id":"W4289670471","doi":"10.48550/arxiv.1809.01494","title":"Interpretation of Natural Language Rules in Conversational Machine\\n Reading","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Task (project management); Reading (process); Interpretation (philosophy); Question answering; Natural (archaeology); Artificial intelligence; Government (linguistics); Natural language processing; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0102487,0.001925164,0.001501569,0.00348558,0.001946293,0.006604413,0.003501049,0.003068487,0.004998393],"category_scores_gemma":[0.04698922,0.001240649,0.00205617,0.001532422,0.002803363,0.009565243,0.003612083,0.003906042,0.003157744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002262143,"about_ca_system_score_gemma":0.002085229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01349336,"about_ca_topic_score_gemma":0.01119483,"domain_scores_codex":[0.9819908,0.01126079,0.0008747625,0.003431348,0.001814438,0.0006277731],"domain_scores_gemma":[0.9568505,0.03417097,0.001413942,0.003938366,0.003042345,0.000583838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001262964,0.001033365,0.01140237,0.002526071,0.0005740944,0.001714155,0.01609191,0.1359432,0.02107762,0.04966661,0.02780301,0.7309046],"study_design_scores_gemma":[0.00009723951,0.0001699159,0.003581229,0.0002058123,0.0001310883,0.0003073773,0.002387724,0.797978,0.01584403,0.1600636,0.01906303,0.0001709304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1416921,0.004841885,0.8003364,0.004067578,0.0006579473,0.001325691,0.004166761,0.01877347,0.02413814],"genre_scores_gemma":[0.6586084,0.0009896441,0.3251162,0.001184549,0.0003625577,0.0006562818,0.008669106,0.0007609735,0.003652206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01349336,"threshold_uncertainty_score":0.05420101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03690349792639731,"score_gpt":0.2000435815320063,"score_spread":0.163140083605609,"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."}}