{"id":"W3175487467","doi":"10.48550/arxiv.2012.09446","title":"Unsupervised Learning of Discourse Structures using a Tree Autoencoder","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Autoencoder; Parsing; Artificial intelligence; Natural language processing; Tree (set theory); Tree structure; Set (abstract data type); Task (project management); Parse tree; Process (computing); Treebank; Annotation; Machine learning; Deep learning; Binary tree","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":[0.0009031022,0.0006712791,0.0005826601,0.0008210157,0.0003726706,0.0006312471,0.0008143325,0.0008611611,0.001338039],"category_scores_gemma":[0.002291304,0.0004845046,0.0008430652,0.0006148143,0.000544515,0.001244488,0.0008589415,0.001928474,0.0007852939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006429768,"about_ca_system_score_gemma":0.0009180016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003208851,"about_ca_topic_score_gemma":0.008072374,"domain_scores_codex":[0.9995642,0.0001513187,0.00001943473,0.0001689792,0.00005595411,0.00004004405],"domain_scores_gemma":[0.9988422,0.0008294811,0.00006781048,0.00008264943,0.0001477824,0.00003025773],"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":[0.0002077173,0.0002167579,0.001857591,0.0001933012,0.0001637479,0.0002306501,0.0004780589,0.3373192,0.03288364,0.01795062,0.005038789,0.60346],"study_design_scores_gemma":[0.000005646121,0.00001857016,0.0002311665,0.00001163183,0.00001171883,0.00001358955,0.00001760215,0.9914041,0.003103232,0.004469948,0.0007075672,0.000005221878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02794846,0.0002747572,0.9683875,0.0002478809,0.00005044773,0.00004772412,0.0002025886,0.001602606,0.001238126],"genre_scores_gemma":[0.4445289,0.000455485,0.5462439,0.000281935,0.0001071769,0.0002414578,0.001848433,0.0002645429,0.006028045],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003208851,"threshold_uncertainty_score":0.00638032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06558740250914832,"score_gpt":0.2152633095578168,"score_spread":0.1496759070486685,"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."}}