{"id":"W3030379882","doi":"","title":"On the Creation of a Corpus for Coherence Evaluation of Discursive Units","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Bank of Canada; National Bank of Canada","funders":"","keywords":"Computer science; Coherence (philosophical gambling strategy); Natural language processing; Artificial intelligence; Sentence; Argument (complex analysis); Focus (optics); Classifier (UML); Linguistics; Textual entailment; Logical consequence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01233511,0.0007641944,0.000889957,0.006426833,0.003077675,0.003905706,0.002206867,0.001634323,0.009484611],"category_scores_gemma":[0.04772181,0.0007733097,0.0004698477,0.003623722,0.002395862,0.006988534,0.005346199,0.001993589,0.003639278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001597498,"about_ca_system_score_gemma":0.003278793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008010175,"about_ca_topic_score_gemma":0.01279062,"domain_scores_codex":[0.9863339,0.008650459,0.00113074,0.00111341,0.002434774,0.00033674],"domain_scores_gemma":[0.9444702,0.03375157,0.001492028,0.005883655,0.01306866,0.001333838],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008691405,0.001313893,0.00950704,0.001427467,0.0001200159,0.000778537,0.011883,0.01145424,0.0596853,0.07109675,0.05890156,0.772963],"study_design_scores_gemma":[0.0007250828,0.001387425,0.03147209,0.001028395,0.0003375647,0.002164219,0.01451746,0.4315942,0.21971,0.07159249,0.2249045,0.0005665644],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2009218,0.0009618101,0.7403103,0.002096623,0.0004093743,0.003829399,0.00969297,0.007953777,0.03382402],"genre_scores_gemma":[0.2721308,0.0003204328,0.7033212,0.0002181776,0.0001199837,0.002702215,0.01305335,0.001549172,0.006584631],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01233511,"threshold_uncertainty_score":0.06523508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05399198577407965,"score_gpt":0.3305914666254582,"score_spread":0.2765994808513786,"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."}}