{"id":"W2949637934","doi":"10.5087/dad.2019.104","title":"How compatible are our discourse annotation frameworks? Insights from mapping RST-DT and PDTB annotations","year":2019,"lang":"en","type":"article","venue":"Dialogue & Discourse","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Treebank; Annotation; Computer science; Rhetorical question; Relation (database); Natural language processing; Resource (disambiguation); Artificial intelligence; Linguistics; Data mining","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":[0.04872491,0.001055138,0.001142186,0.007927607,0.004958651,0.0146046,0.00303171,0.002958879,0.00668972],"category_scores_gemma":[0.156378,0.001405438,0.0009851481,0.007651697,0.005577852,0.02027694,0.008133505,0.004760646,0.002010665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005067472,"about_ca_system_score_gemma":0.005730564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01568007,"about_ca_topic_score_gemma":0.01499428,"domain_scores_codex":[0.9409975,0.04287031,0.002790053,0.005304534,0.006510457,0.001527162],"domain_scores_gemma":[0.8758059,0.08424418,0.005309265,0.02157288,0.01150205,0.001565757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0008775321,0.0002268313,0.0240212,0.001169961,0.0002074431,0.0007145589,0.07549348,0.01242501,0.01853564,0.5607303,0.009149878,0.2964482],"study_design_scores_gemma":[0.0001172627,0.0001798649,0.02775147,0.001505803,0.0002448594,0.0008237995,0.04102046,0.1501431,0.0232222,0.6209368,0.1336604,0.0003940435],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1371805,0.002088589,0.7805164,0.01040743,0.0003319677,0.00045412,0.003212524,0.002419059,0.06338934],"genre_scores_gemma":[0.6407163,0.0009235807,0.3487906,0.0005578442,0.00008878385,0.0006479772,0.003239642,0.001376877,0.003658463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04872491,"threshold_uncertainty_score":0.257685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0142119105583365,"score_gpt":0.2761876015369167,"score_spread":0.2619756909785802,"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."}}