{"id":"W2803395921","doi":"10.18653/v1/s18-2001","title":"Resolving Event Coreference with Supervised Representation Learning and Clustering-Oriented Regularization","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Coreference; Cluster analysis; Computer science; Artificial intelligence; Regularization (linguistics); Event (particle physics); Representation (politics); Machine learning; Natural language processing; Feature learning; Resolution (logic)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003425959,0.0002241685,0.0002273937,0.0001464915,0.0001777287,0.0003381591,0.0004520105,0.0001638949,0.0000214117],"category_scores_gemma":[0.0001117325,0.0001984453,0.0000307711,0.0001971395,0.00005086615,0.0003146279,0.001923121,0.0003808357,0.000004409236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006971147,"about_ca_system_score_gemma":0.0001013769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001354026,"about_ca_topic_score_gemma":0.00006564461,"domain_scores_codex":[0.9979002,0.0001464857,0.0003335564,0.0009804992,0.0004031179,0.0002361104],"domain_scores_gemma":[0.9986095,0.00006070748,0.000218811,0.0007479338,0.0002752806,0.00008775735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003980035,0.0002896673,0.1384747,0.001859627,0.0004706342,0.0001338537,0.04182876,0.4211317,0.005497145,0.08341074,0.00103125,0.305474],"study_design_scores_gemma":[0.0002822939,0.00008137351,0.001731917,0.000288906,0.00001160737,0.00001320279,0.00011077,0.9948915,0.0005072771,0.001601182,0.0002244961,0.0002554328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05719929,0.00004649786,0.9398036,0.0003936816,0.0003189291,0.0003316042,5.125768e-7,0.0003205977,0.001585288],"genre_scores_gemma":[0.6383478,0.00004841925,0.3599218,0.00007227944,0.0001221056,0.00003253502,0.0000382482,0.00001984597,0.001397042],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5811485,"threshold_uncertainty_score":0.8092363,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03039245407117697,"score_gpt":0.2756032686607547,"score_spread":0.2452108145895777,"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."}}