{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004063481,0.0004426379,0.0004517608,0.0001596818,0.0004205419,0.0005803253,0.003836408,0.0002013569,0.0002292819],"category_scores_gemma":[0.0002483669,0.0003625622,0.0002040918,0.0003985258,0.0001823286,0.0005074405,0.003800029,0.001181775,0.000004411901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000269204,"about_ca_system_score_gemma":0.0002756805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008905635,"about_ca_topic_score_gemma":0.00005162578,"domain_scores_codex":[0.9961693,0.00005357813,0.0009557385,0.001236854,0.001160665,0.0004238595],"domain_scores_gemma":[0.9975703,0.0001010085,0.0009561356,0.0008144147,0.0004535502,0.000104629],"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":[0.0001390848,0.0003378383,0.0132528,0.0004455549,0.0001390978,0.000006511756,0.0208033,0.0374135,0.3418012,0.4625818,0.0000362157,0.1230431],"study_design_scores_gemma":[0.00002704595,0.00005435149,0.0002403885,0.0005792042,0.0000382706,0.000002197327,0.002563986,0.6662207,0.1477029,0.1822347,0.000007247616,0.0003290249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8482344,0.00007549467,0.1466248,0.001265622,0.00252012,0.0006889015,0.00009842835,0.0001103068,0.0003819889],"genre_scores_gemma":[0.9767809,0.00004290769,0.02271717,0.0001114014,0.0002332785,0.00002990319,0.00001142947,0.0000244664,0.00004852721],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6288072,"threshold_uncertainty_score":0.9998826,"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."}}