{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00299932,0.001275224,0.0008232433,0.002616321,0.000790463,0.001505916,0.001630439,0.001891713,0.004024601],"category_scores_gemma":[0.01211109,0.0006821056,0.0009656653,0.002309757,0.0006529929,0.005899922,0.002365189,0.003206738,0.002492788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00134095,"about_ca_system_score_gemma":0.002010398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003903892,"about_ca_topic_score_gemma":0.01040446,"domain_scores_codex":[0.998726,0.0006008011,0.00007944907,0.0003885939,0.0001395961,0.00006552565],"domain_scores_gemma":[0.992726,0.005565066,0.0002927204,0.0006319013,0.0006140989,0.0001701795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004479373,0.0004692228,0.004835555,0.0009361022,0.000160706,0.0002477611,0.001196341,0.1968786,0.02665985,0.02175831,0.03261766,0.7137919],"study_design_scores_gemma":[0.00004442573,0.00006008464,0.000684779,0.0000609769,0.00003497858,0.00003336103,0.0002129505,0.9666798,0.007959185,0.01874937,0.005465836,0.00001441648],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09729013,0.001099358,0.8657681,0.001122741,0.0001484819,0.0003921245,0.004378611,0.02395208,0.00584845],"genre_scores_gemma":[0.3019505,0.0004870227,0.6743424,0.0004129081,0.0001271575,0.0006168774,0.01655018,0.00102801,0.004484869],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004024601,"threshold_uncertainty_score":0.01586211,"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."}}