{"id":"W4386566755","doi":"10.18653/v1/2023.eacl-main.125","title":"What happens before and after: Multi-Event Commonsense in Event Coreference Resolution","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Coreference; Computer science; Event (particle physics); Leverage (statistics); Natural language processing; Artificial intelligence; Commonsense knowledge; Commonsense reasoning; Sentence; Resolution (logic); Knowledge-based systems","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":[0.003779149,0.0008366255,0.0007783326,0.002026541,0.001753094,0.00225292,0.003158163,0.00238103,0.004570787],"category_scores_gemma":[0.01676484,0.0008272282,0.001632365,0.001965733,0.001527404,0.006784304,0.004003844,0.002876635,0.0009423901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001117443,"about_ca_system_score_gemma":0.001107827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005521624,"about_ca_topic_score_gemma":0.008404576,"domain_scores_codex":[0.9972952,0.001029093,0.0001288168,0.00101424,0.0003704439,0.0001621152],"domain_scores_gemma":[0.9914528,0.0062507,0.0005100765,0.001145037,0.0004890136,0.0001522464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001205089,0.0002737914,0.01421362,0.0006643914,0.000498921,0.003454472,0.01078371,0.2208467,0.01760209,0.3685266,0.01287509,0.3490556],"study_design_scores_gemma":[0.00003268208,0.00003468289,0.001753042,0.00006889037,0.0001232951,0.0006531563,0.0007099426,0.7682244,0.008765472,0.2088587,0.01069657,0.00007932311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03817085,0.000386112,0.9550812,0.0007406565,0.00008495379,0.00006804027,0.000425287,0.001018409,0.00402455],"genre_scores_gemma":[0.736366,0.0002870072,0.2584594,0.0002955441,0.0001335458,0.0001059061,0.001123647,0.0002904459,0.002938535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005521624,"threshold_uncertainty_score":0.01998627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04628439186879934,"score_gpt":0.2907679184297647,"score_spread":0.2444835265609654,"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."}}