{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009737079,0.00008691274,0.0001684166,0.0000862018,0.0001903977,0.0001228021,0.0005440338,0.00006672897,0.00002835179],"category_scores_gemma":[0.0004370071,0.00007379581,0.00003706739,0.00009930004,0.0001079185,0.0003575169,0.0001652716,0.00008700279,0.000001445877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001583848,"about_ca_system_score_gemma":0.00004144523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003343395,"about_ca_topic_score_gemma":0.00003480937,"domain_scores_codex":[0.9989318,0.00008717026,0.000251595,0.0002033783,0.0004169203,0.0001090938],"domain_scores_gemma":[0.9985895,0.0001109907,0.000570457,0.0004490203,0.0002442963,0.00003577621],"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":[0.00003539021,0.0000795824,0.006584845,0.0002036401,0.00004933609,0.000009851588,0.02293183,0.0003563767,0.4030734,0.008786154,0.0001127954,0.5577768],"study_design_scores_gemma":[0.001426477,0.0004817624,0.02025079,0.001394423,0.0001776775,0.0000339379,0.00101279,0.4388496,0.4751555,0.06036011,0.0002621976,0.0005947456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9048939,0.01362066,0.07961407,0.0002317042,0.0000503868,0.0002979668,0.000006865991,0.00008407338,0.00120036],"genre_scores_gemma":[0.9446278,0.00002433512,0.05514988,0.00001675076,0.00002720298,0.00001030114,0.000003723633,0.000005252842,0.0001348107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5571821,"threshold_uncertainty_score":0.3009306,"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."}}