{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001472014,0.00007014058,0.0001055396,0.00004106939,0.00005791857,0.00003419262,0.0002407631,0.00003807439,0.00001521203],"category_scores_gemma":[0.001669672,0.00004513741,0.00002330655,0.0003152666,0.0000451323,0.0001197769,0.00004695754,0.00005137575,4.102329e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002014944,"about_ca_system_score_gemma":0.00005250784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000390507,"about_ca_topic_score_gemma":0.000008061206,"domain_scores_codex":[0.9987492,0.0002210793,0.0001675063,0.0001698823,0.0006204004,0.0000719337],"domain_scores_gemma":[0.9985774,0.0003165824,0.0002442597,0.0001783596,0.0006590853,0.00002427759],"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":[0.00009923928,0.0000364837,0.0001310631,0.0001407272,0.00003157355,3.003618e-7,0.05452024,0.0007156392,0.03800471,0.03769985,0.0002913076,0.8683289],"study_design_scores_gemma":[0.0006651152,0.0004293285,0.0006366202,0.0001424206,0.0001146299,0.000001288019,0.001562123,0.875591,0.09011885,0.03057669,0.00005447091,0.0001074962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9004104,0.005382247,0.09077033,0.001834669,0.00003010216,0.001170785,0.00001407554,0.00005119385,0.000336164],"genre_scores_gemma":[0.992542,0.000006610713,0.007191289,0.0001398028,0.00002784168,0.00006784746,0.00001408515,0.000004265643,0.00000620519],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8748753,"threshold_uncertainty_score":0.1998874,"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."}}