{"id":"W3098396746","doi":"10.18653/v1/2020.emnlp-main.551","title":"Distilling Structured Knowledge for Text-Based Relational Reasoning","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Canadian Institute for Advanced Research; Compute Canada; Microsoft Research","keywords":"Computer science; Artificial intelligence; Natural language processing; Benchmark (surveying); Task (project management); Statistical relational learning; Machine learning; Relational database; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001841256,0.001473029,0.000705339,0.002752152,0.0006120533,0.001758136,0.002781794,0.001628106,0.00611332],"category_scores_gemma":[0.009024005,0.0005055218,0.002044196,0.002157933,0.0008469356,0.008308657,0.002555942,0.002809694,0.003250178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001631793,"about_ca_system_score_gemma":0.001477184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006445646,"about_ca_topic_score_gemma":0.0122136,"domain_scores_codex":[0.9986361,0.0004235614,0.0001085371,0.0004737769,0.0002805227,0.00007754883],"domain_scores_gemma":[0.9964852,0.002347902,0.000201216,0.0005661077,0.0003166461,0.00008285342],"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":[0.0003744748,0.0004621697,0.002196715,0.001276334,0.00024354,0.0006993085,0.0009313005,0.2373242,0.0214895,0.04545273,0.02955667,0.6599931],"study_design_scores_gemma":[0.00003809488,0.00003967909,0.0003476846,0.00006861755,0.00005496109,0.0001025677,0.0001496387,0.9200101,0.008311138,0.06259636,0.008258485,0.00002258261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03310477,0.001342831,0.9418619,0.001478357,0.0001574978,0.0002544033,0.004349867,0.01258054,0.004869839],"genre_scores_gemma":[0.3524584,0.001071823,0.6227279,0.0006689418,0.0001686318,0.0002691672,0.01853182,0.0005448524,0.003558537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006445646,"threshold_uncertainty_score":0.02045107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04633304072299972,"score_gpt":0.2667868192989307,"score_spread":0.220453778575931,"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."}}