{"id":"W2251211118","doi":"","title":"Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis","year":2013,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Parsing; Computer science; Natural language processing; Artificial intelligence; Bottom-up parsing; Top-down parsing; Parser combinator; Rhetorical question; Set (abstract data type); S-attributed grammar; Margin (machine learning); Tree (set theory); Programming language; Linguistics; Machine learning","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":[0.009100784,0.002100671,0.001657692,0.005048881,0.001319063,0.005586059,0.002762497,0.00274305,0.00402024],"category_scores_gemma":[0.02076046,0.001203144,0.001756972,0.002980184,0.001950686,0.008991417,0.004043401,0.003843949,0.004796571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262775,"about_ca_system_score_gemma":0.003684237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002536133,"about_ca_topic_score_gemma":0.004515996,"domain_scores_codex":[0.9933805,0.003540388,0.0004625756,0.00125194,0.0011035,0.00026106],"domain_scores_gemma":[0.9796419,0.01373058,0.0009053036,0.002875073,0.002522374,0.0003247853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002325722,0.0003954407,0.003567179,0.000887069,0.0002662636,0.0004090591,0.002171272,0.03214833,0.0386819,0.06505278,0.01457894,0.8416092],"study_design_scores_gemma":[0.00007938543,0.0001437138,0.001563285,0.0001673953,0.0002194531,0.0003883778,0.000427903,0.7310262,0.06265023,0.1679478,0.03516026,0.000225876],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003398711,0.0002632821,0.9905912,0.0003658351,0.00005142021,0.00009603317,0.0002482319,0.004039682,0.0009456073],"genre_scores_gemma":[0.05329413,0.0001975184,0.9434916,0.0001477134,0.000106782,0.0001316765,0.0008551666,0.0006733431,0.001102092],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009100784,"threshold_uncertainty_score":0.0481301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03722023247038017,"score_gpt":0.3307246162578211,"score_spread":0.2935043837874409,"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."}}