{"id":"W3101384737","doi":"10.18653/v1/2020.findings-emnlp.281","title":"Towards Domain-Independent Text Structuring Trainable on Large Discourse Treebanks","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Structuring; Computer science; Pointer (user interface); Task (project management); Dependency (UML); Artificial intelligence; Metric (unit); Natural language processing; Set (abstract data type); Domain (mathematical analysis); Tree (set theory); Machine learning; Programming language","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":[0.0001669925,0.0001624138,0.0001674008,0.0000489163,0.0001335787,0.0001764223,0.0008981525,0.00005891877,0.0002403271],"category_scores_gemma":[0.00001928288,0.0001326157,0.00007985254,0.0001689372,0.00001455069,0.0003438182,0.0003490631,0.0002113925,0.00009628211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005335292,"about_ca_system_score_gemma":0.00007444319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004066283,"about_ca_topic_score_gemma":0.00002185966,"domain_scores_codex":[0.9983543,0.00003567455,0.0002050936,0.0005418927,0.0004312388,0.0004317896],"domain_scores_gemma":[0.9992117,0.00001941946,0.00004473078,0.0004913366,0.00002276641,0.0002101045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000012373,0.00006719424,0.0001553537,0.0000278314,0.00002360203,0.0001284707,0.006522825,0.002419968,0.000733981,0.8723343,0.0008815028,0.1166926],"study_design_scores_gemma":[0.004016246,0.0006162763,0.004391511,0.00006012319,0.00002016527,0.00004932424,0.003946965,0.8864632,0.01734017,0.05122915,0.03043938,0.001427534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.111861,0.00001986523,0.8396123,0.01030851,0.0002193334,0.0001411728,0.000002734946,0.000268022,0.03756705],"genre_scores_gemma":[0.9538099,0.000001517965,0.04289292,0.002363732,0.0001881149,0.000006540464,0.000001006262,0.00001121792,0.0007251057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8840432,"threshold_uncertainty_score":0.5407913,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02345598499062612,"score_gpt":0.2601611443171873,"score_spread":0.2367051593265612,"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."}}