{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003388693,0.00009360797,0.0001088165,0.0001231872,0.00004863387,0.000132956,0.0002464032,0.00004866906,0.000007112213],"category_scores_gemma":[0.00002200896,0.00008335119,0.00002387067,0.0002723446,0.0000255107,0.0004510102,0.0004349786,0.0001064812,0.00006066942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004693794,"about_ca_system_score_gemma":0.00002658545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001801685,"about_ca_topic_score_gemma":0.005765672,"domain_scores_codex":[0.9989771,0.00005686281,0.0002090396,0.0003357406,0.0001670959,0.0002542176],"domain_scores_gemma":[0.9994346,0.00004099979,0.00003219583,0.0003978731,0.00002391871,0.00007042255],"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":[0.00008970504,0.0004572231,0.2034695,0.0001823559,0.00003676372,0.0008802963,0.03806315,0.01808149,0.0009184781,0.0993956,0.00244242,0.635983],"study_design_scores_gemma":[0.0002617146,0.00003064383,0.1476787,0.00008278418,0.000001018604,0.000009792139,0.0002330057,0.8494865,0.00005305446,0.001666606,0.0004025816,0.00009360309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7160594,0.0001051414,0.2800915,0.003034627,0.000324451,0.0001664054,8.888563e-7,0.0001651004,0.00005245194],"genre_scores_gemma":[0.985274,0.00009953905,0.01365769,0.0002443061,0.00001348686,0.0000225934,0.000002171053,0.000004688894,0.0006815728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.831405,"threshold_uncertainty_score":0.3398963,"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."}}