{"id":"W4283802444","doi":"10.1609/aaai.v36i10.21325","title":"Predicting Above-Sentence Discourse Structure Using Distant Supervision from Topic Segmentation","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Natural language processing; Computer science; Paragraph; Sentence; Parsing; Automatic summarization; Artificial intelligence; Segmentation; Task (project management); Semantic role labeling; Linguistics","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":[0.0000978497,0.0000941839,0.00008767454,0.0000431964,0.0003376353,0.000113177,0.0005188399,0.00001878855,0.0002661342],"category_scores_gemma":[0.00001014018,0.00008508489,0.00003247022,0.0001648787,0.00001191041,0.0004693727,0.0005819506,0.0001483248,0.000001209613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001245087,"about_ca_system_score_gemma":0.00004328113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008594693,"about_ca_topic_score_gemma":0.00005764252,"domain_scores_codex":[0.9987596,0.00006508286,0.0001975511,0.0003865807,0.0004115496,0.000179629],"domain_scores_gemma":[0.9994223,0.00003596684,0.0000638918,0.00040793,0.00002167429,0.00004822068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002428777,0.0001537838,0.231773,0.00003513596,0.00006205605,0.0000950275,0.02000739,0.2060082,0.3679264,0.0381894,0.0001524272,0.135573],"study_design_scores_gemma":[0.0001919942,0.00002118831,0.002040932,0.000008720074,0.000005643558,0.000007628835,0.00167237,0.9896303,0.002984162,0.003265678,0.00005610795,0.0001153004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.53488,0.00003930375,0.4641502,0.0002272095,0.0005073083,0.0000697474,0.00001099322,0.00006136853,0.00005388911],"genre_scores_gemma":[0.8973522,0.000001321954,0.1022705,0.0001973799,0.00008873078,0.000004013966,0.00001432821,0.000005545088,0.00006608536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7836221,"threshold_uncertainty_score":0.3469661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02308686032587811,"score_gpt":0.2733598464726859,"score_spread":0.2502729861468078,"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."}}