{"id":"W4389524397","doi":"10.18653/v1/2023.emnlp-main.100","title":"Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Bridging (networking); Natural language processing; Artificial intelligence; Machine translation; Task (project management); Information retrieval; Knowledge graph; Question answering; Benchmark (surveying); Entity linking; Quality (philosophy); Knowledge base","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009119323,0.001478868,0.001451857,0.01171833,0.001911518,0.003694525,0.002312832,0.002176137,0.002405713],"category_scores_gemma":[0.0850502,0.000782515,0.001567198,0.00776727,0.002059838,0.01108589,0.005566952,0.002807466,0.001362336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002208197,"about_ca_system_score_gemma":0.00217639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01819007,"about_ca_topic_score_gemma":0.0266396,"domain_scores_codex":[0.9866882,0.004853086,0.001016105,0.004563187,0.002421609,0.0004577513],"domain_scores_gemma":[0.9092093,0.06587023,0.003610966,0.01264417,0.007817511,0.0008478952],"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":[0.001775295,0.0008302808,0.03703432,0.006787893,0.001619948,0.001204086,0.006295579,0.1734231,0.02885446,0.02026097,0.05989195,0.6620221],"study_design_scores_gemma":[0.0002902247,0.0005286506,0.03053438,0.0009029311,0.001212062,0.001339976,0.003878157,0.7052765,0.0983213,0.07962406,0.07778316,0.0003085701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5192822,0.01123977,0.3815017,0.003724142,0.0004505695,0.0003376543,0.02262465,0.04122806,0.0196112],"genre_scores_gemma":[0.7644419,0.002027623,0.1795328,0.0005759143,0.000148817,0.0001671485,0.04775798,0.002719406,0.002628295],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01819007,"threshold_uncertainty_score":0.04822814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02036285220120925,"score_gpt":0.277810869769017,"score_spread":0.2574480175678077,"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."}}