{"id":"W4200631513","doi":"10.1609/aaai.v36i10.21325","title":"Predicting Above-Sentence Discourse Structure Using Distant Supervision from Topic Segmentation","year":2022,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"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; Artificial intelligence; Automatic summarization; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001260806,0.001006453,0.0005593376,0.001990953,0.0007728003,0.001081976,0.0006702397,0.001134438,0.002449255],"category_scores_gemma":[0.004931436,0.0003922715,0.0006789248,0.00116037,0.0003890255,0.002124448,0.0008883677,0.001464041,0.002196301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00059062,"about_ca_system_score_gemma":0.0009635864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00377335,"about_ca_topic_score_gemma":0.008955548,"domain_scores_codex":[0.9993451,0.0002492055,0.00003489426,0.0002518544,0.0000614904,0.00005740813],"domain_scores_gemma":[0.9960036,0.002631008,0.0003728186,0.0002436724,0.0005821594,0.0001667359],"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":[0.002114728,0.0008138742,0.03872112,0.00118238,0.0003015852,0.001003457,0.004869716,0.06647521,0.09946089,0.009764893,0.03962839,0.7356638],"study_design_scores_gemma":[0.00008701519,0.0002196507,0.01534039,0.0001034585,0.0001617226,0.0001857169,0.0006856148,0.9285061,0.02667858,0.01558186,0.0123992,0.00005074302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4832378,0.004369478,0.4872331,0.001721005,0.0003811684,0.0002842459,0.006235954,0.007350455,0.009186856],"genre_scores_gemma":[0.8655366,0.0006526701,0.1172544,0.0001528909,0.0003669798,0.0001811691,0.01106633,0.000326082,0.004462893],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00377335,"threshold_uncertainty_score":0.008193552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09739871542539401,"score_gpt":0.3301161282984262,"score_spread":0.2327174128730322,"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."}}