{"id":"W3138967041","doi":"10.18653/v1/2021.naacl-main.43","title":"Open Domain Question Answering over Tables via Dense Retrieval","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Labrador Retriever; Information retrieval; Computer science; Context (archaeology); Domain (mathematical analysis); Precision and recall; Table (database); Question answering; Data mining; Mathematics; Geography; Medicine","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":[0.002828617,0.001228641,0.002830312,0.005333333,0.001371264,0.005225583,0.002578949,0.001984779,0.01064515],"category_scores_gemma":[0.01610393,0.001142507,0.001809249,0.006616801,0.001229607,0.01581385,0.007117906,0.002338378,0.007132121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382429,"about_ca_system_score_gemma":0.001674668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007384731,"about_ca_topic_score_gemma":0.01208393,"domain_scores_codex":[0.9961889,0.001371477,0.0003152131,0.0009086194,0.0008596046,0.0003562226],"domain_scores_gemma":[0.9899353,0.006198213,0.0002946218,0.002376169,0.0009117097,0.0002838708],"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":[0.00126773,0.0008364239,0.004059322,0.001363114,0.0004247413,0.0004774529,0.001677467,0.04430997,0.01421303,0.09904152,0.1499406,0.6823885],"study_design_scores_gemma":[0.0002224519,0.0001903215,0.001365319,0.0001251254,0.0002109242,0.0002983981,0.0009505177,0.4854228,0.007628048,0.4762982,0.02720976,0.00007807285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06692385,0.006565018,0.8774198,0.003694521,0.000315967,0.0004973116,0.01381496,0.01975565,0.01101295],"genre_scores_gemma":[0.4792808,0.002595858,0.4579264,0.0009769913,0.0006200943,0.0003815764,0.04720658,0.000887031,0.01012475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01064515,"threshold_uncertainty_score":0.03561157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02808576002442507,"score_gpt":0.292897135530809,"score_spread":0.264811375506384,"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."}}