{"id":"W2964270503","doi":"10.26615/978-954-452-049-6_054","title":"Improving Discourse Relation Projection to Build Discourse Annotated Corpora","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Annotation; Natural language processing; Classifier (UML); Artificial intelligence; Parallel corpora; Intersection (aeronautics); Relation (database); Machine translation; Linguistics","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":[0.0003137574,0.0001442272,0.000119615,0.0001400978,0.000540922,0.0008966182,0.001161444,0.00007680614,0.000006009011],"category_scores_gemma":[0.0002388777,0.0001129119,0.0000386251,0.0001822344,0.0000635806,0.00242664,0.0004786509,0.0001825104,0.00003053246],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007014214,"about_ca_system_score_gemma":0.00007287712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006921557,"about_ca_topic_score_gemma":0.00008528017,"domain_scores_codex":[0.9988481,0.0000270666,0.0001816357,0.0004419392,0.0002544167,0.0002468774],"domain_scores_gemma":[0.9984823,0.00001629625,0.0002640919,0.001017499,0.0001271404,0.00009268831],"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":[0.00003366026,0.0001167403,0.0052751,0.0000393288,0.00001554049,0.00005569413,0.001498189,0.00001786803,0.06953423,0.1353119,0.003270148,0.7848316],"study_design_scores_gemma":[0.001707173,0.001100681,0.04171132,0.0006451842,0.00007666969,0.0002020327,0.0005581065,0.4126417,0.4296917,0.1072522,0.001475241,0.002937991],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04156727,0.00004977521,0.9503302,0.004958871,0.0003664167,0.000376692,0.000001493818,0.001007853,0.001341435],"genre_scores_gemma":[0.6097357,7.782517e-7,0.3888079,0.0001155494,0.00006416706,0.00001967934,0.000002406418,0.000008742089,0.001245049],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7818936,"threshold_uncertainty_score":0.864611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01701369306538897,"score_gpt":0.3263320920225469,"score_spread":0.309318398957158,"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."}}