{"id":"W2517784737","doi":"10.18653/v1/k16-1024","title":"Event Linking with Sentential Features from Convolutional Neural Networks","year":2016,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; Bundesministerium für Bildung und Forschung","keywords":"Coreference; Computer science; Pairwise comparison; Artificial intelligence; Event (particle physics); Convolutional neural network; Context (archaeology); Natural language processing; Similarity (geometry); Feature (linguistics); Task (project management); Process (computing); Machine learning; Resolution (logic); Image (mathematics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006274382,0.00008572023,0.00007709124,0.00002318382,0.00006844974,0.00006977894,0.0003789012,0.00004079112,0.00004612389],"category_scores_gemma":[0.000004390214,0.00004688599,0.00003578972,0.00005651834,0.00002539062,0.0002552435,0.0001698546,0.00007556839,0.00001072408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002564838,"about_ca_system_score_gemma":0.00002447375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009229501,"about_ca_topic_score_gemma":0.00008676077,"domain_scores_codex":[0.9991428,0.00002698786,0.0001098648,0.0002928042,0.0002229195,0.0002045931],"domain_scores_gemma":[0.9995056,0.00006763625,0.00003855593,0.0002845128,0.00004358728,0.00006015292],"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":[0.0001010792,0.000134053,0.08542653,0.000007351,0.000199672,0.0001279792,0.0004795257,0.101578,0.003277963,0.3371297,0.004497569,0.4670405],"study_design_scores_gemma":[0.0005491543,0.00002989624,0.01531896,0.00004063751,0.000004760061,0.00002121113,0.000005693238,0.9809927,0.0002127314,0.002280647,0.0003911059,0.0001525389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0414849,0.00008166371,0.9552453,0.002190795,0.0005140241,0.00005105662,8.828901e-7,0.0001287177,0.0003026618],"genre_scores_gemma":[0.9561458,0.000002418428,0.04237528,0.0004472443,0.0003894478,0.000003357457,0.000001921774,0.000004359431,0.0006302132],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9146609,"threshold_uncertainty_score":0.1911955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01122827669467524,"score_gpt":0.2121893518677359,"score_spread":0.2009610751730607,"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."}}