{"id":"W3111446732","doi":"10.1609/aaai.v35i14.17549","title":"Unsupervised Learning of Discourse Structures using a Tree Autoencoder","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Huawei Technologies","keywords":"Computer science; Autoencoder; Parsing; Artificial intelligence; Natural language processing; Tree (set theory); Set (abstract data type); Tree structure; Task (project management); Process (computing); Parse tree; Annotation; Deep learning; Binary tree","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":[0.0009272683,0.000670072,0.0005830365,0.0008375887,0.0003693292,0.0006474291,0.0008196868,0.0008425094,0.001263736],"category_scores_gemma":[0.00225679,0.0004794183,0.0008473639,0.000630165,0.0005123765,0.001261471,0.0008495387,0.001884091,0.0007438606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006354104,"about_ca_system_score_gemma":0.0009271981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003409156,"about_ca_topic_score_gemma":0.008003305,"domain_scores_codex":[0.9995763,0.0001463442,0.00001915812,0.0001641755,0.00005422678,0.00003982885],"domain_scores_gemma":[0.9989111,0.0007778173,0.0000628704,0.00007593055,0.0001430466,0.00002922613],"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":[0.0002108737,0.0002052109,0.001886951,0.0001930374,0.0001679401,0.0002201629,0.0005234558,0.3414971,0.03280178,0.01799848,0.004896228,0.5993987],"study_design_scores_gemma":[0.000005882236,0.00001769048,0.0002393477,0.00001103723,0.00001223339,0.00001315091,0.00001814754,0.9918223,0.003031178,0.00411515,0.0007084375,0.000005438643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03166223,0.0003024013,0.9644462,0.0002573608,0.00005414987,0.00005493781,0.0002175634,0.001659209,0.001345917],"genre_scores_gemma":[0.4674613,0.0004888614,0.5234103,0.0002664482,0.0001128504,0.0002663229,0.001842457,0.0002627765,0.00588869],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003409156,"threshold_uncertainty_score":0.006778598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1065955135151079,"score_gpt":0.323993007079681,"score_spread":0.2173974935645731,"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."}}