{"id":"W3153874716","doi":"10.48550/arxiv.2104.07058","title":"Predicting Discourse Trees from Transformer-based Neural Summarizers","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automatic summarization; Computer science; Transformer; Natural language processing; Artificial intelligence; Discourse analysis; Style (visual arts); Dependency (UML); Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001607082,0.0003830101,0.0004122716,0.0001892221,0.0001812067,0.0002839317,0.002012979,0.0002983443,0.00004864611],"category_scores_gemma":[0.00002879718,0.0004491442,0.0003734066,0.0003825602,0.0001035054,0.0005956553,0.0006793864,0.0007867217,0.000008906339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001862943,"about_ca_system_score_gemma":0.0004043493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001919941,"about_ca_topic_score_gemma":0.0009464264,"domain_scores_codex":[0.997408,0.0001706097,0.0002739558,0.001524773,0.0001676993,0.000454937],"domain_scores_gemma":[0.9978282,0.0001692364,0.0001957783,0.001491031,0.00009891302,0.0002167861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002383231,0.0001007929,0.02683031,0.00004723796,0.0001175664,0.0006609003,0.0008199326,0.9622118,0.0002156236,0.005023055,0.00002032523,0.003928628],"study_design_scores_gemma":[0.000591674,0.00002373347,0.00192761,0.0001460442,0.00009690008,0.000001170516,0.000393843,0.9936264,0.0003732894,0.002349587,0.00002892399,0.0004408082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4946761,0.00005378205,0.5036287,0.0002068927,0.0006182677,0.0001273956,0.00002208807,0.0002096302,0.0004571124],"genre_scores_gemma":[0.9933063,0.00003235883,0.006049594,0.0001342651,0.0001357992,0.0000012454,0.00007297444,0.00002277905,0.000244625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4986303,"threshold_uncertainty_score":0.999796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06890917542870136,"score_gpt":0.1956830011154065,"score_spread":0.1267738256867052,"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."}}