{"id":"W2583305969","doi":"10.1007/s10579-017-9383-x","title":"RST Signalling Corpus: a corpus of signals of coherence relations","year":2017,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Treebank; Annotation; Corpus linguistics; Natural language processing; Computer science; Parsing; Coherence (philosophical gambling strategy); Artificial intelligence; Text corpus; Linguistics; British National Corpus","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002075363,0.001164985,0.0008034284,0.004286251,0.001530585,0.00207248,0.001655261,0.002553018,0.03060549],"category_scores_gemma":[0.01715668,0.0006566732,0.0004862276,0.003571222,0.00130829,0.002169056,0.002101392,0.001761684,0.01435447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044953,"about_ca_system_score_gemma":0.002350146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009325515,"about_ca_topic_score_gemma":0.01063891,"domain_scores_codex":[0.9972509,0.0008702228,0.0003310136,0.0004656031,0.0009038898,0.0001785056],"domain_scores_gemma":[0.9850116,0.009570358,0.0007219234,0.00213418,0.002116461,0.0004455129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003904845,0.0009018078,0.00634534,0.008438109,0.0003241394,0.0026162,0.00806343,0.005638235,0.147798,0.04604514,0.4653592,0.3045656],"study_design_scores_gemma":[0.001108444,0.0005845534,0.0727355,0.0008517589,0.0004819446,0.004267394,0.00380409,0.01848018,0.07631247,0.01480362,0.8060129,0.0005571572],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2560739,0.0047461,0.08869983,0.003343754,0.001355171,0.001667574,0.5526342,0.01364039,0.07783917],"genre_scores_gemma":[0.4079369,0.001622593,0.0760173,0.0007212487,0.0005373625,0.002497724,0.4724433,0.002643691,0.03557991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03060549,"threshold_uncertainty_score":0.1023856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03078082295855368,"score_gpt":0.3193694584320568,"score_spread":0.2885886354735031,"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."}}