{"id":"W2515353635","doi":"10.18653/v1/k16-2022","title":"Discourse Relation Sense Classification Systems for CoNLL-2016 Shared Task","year":2016,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; Atomic Energy of Canada Limited; National Natural Science Foundation of China; University of Pennsylvania","keywords":"Computer science; Task (project management); Natural language processing; Discriminative model; Artificial intelligence; Relation (database); Beijing; Linguistics; China; Data mining","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005095376,0.00266458,0.001620043,0.003937799,0.002296605,0.002282588,0.002606909,0.002266144,0.007422647],"category_scores_gemma":[0.01081588,0.0004353967,0.001273273,0.002228974,0.0006578756,0.005550954,0.004656314,0.003419289,0.005928054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001789175,"about_ca_system_score_gemma":0.002668326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006933751,"about_ca_topic_score_gemma":0.01187403,"domain_scores_codex":[0.9947923,0.001434545,0.0005825476,0.001857365,0.0009110787,0.0004221176],"domain_scores_gemma":[0.9942594,0.001720789,0.0003622831,0.001613882,0.001618366,0.000425347],"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":[0.001325697,0.001027104,0.003630479,0.0009131328,0.0002003785,0.000496663,0.001166644,0.004760883,0.03708472,0.00478129,0.07924585,0.8653672],"study_design_scores_gemma":[0.000923137,0.002019565,0.01704747,0.000426353,0.0006033158,0.0009997319,0.004658828,0.7239829,0.1092447,0.02892797,0.1107603,0.0004056395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4037355,0.01015206,0.4239488,0.004050093,0.004284467,0.003879787,0.0259038,0.08345774,0.0405877],"genre_scores_gemma":[0.5949566,0.000956102,0.3231633,0.00077332,0.000628272,0.002097944,0.0601318,0.001209745,0.01608296],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007422647,"threshold_uncertainty_score":0.02694726,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02597508335173711,"score_gpt":0.2996771960466668,"score_spread":0.2737021126949297,"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."}}