{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000320923,0.0001970277,0.0003090884,0.0001046858,0.0001630372,0.0001612467,0.00146208,0.00008534503,0.00006713067],"category_scores_gemma":[0.0004937228,0.0001538324,0.0001442186,0.0006336926,0.0002157356,0.0003747571,0.0005223974,0.0003371594,0.000005531826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003618408,"about_ca_system_score_gemma":0.000263917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006177033,"about_ca_topic_score_gemma":0.00001085217,"domain_scores_codex":[0.998058,0.00003267618,0.0005735272,0.0004927668,0.0005386092,0.0003044039],"domain_scores_gemma":[0.9983332,0.00007434746,0.0003784125,0.0003550218,0.0007886844,0.00007037914],"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":[0.00001497132,0.00006465799,0.000497757,0.0000495811,0.00001734813,0.000001170143,0.002352029,0.004847385,0.1810911,0.7554113,0.000005444424,0.05564725],"study_design_scores_gemma":[0.00001948375,0.00003799942,0.000126874,0.000142783,0.00001105591,0.000006198926,0.001036678,0.4922849,0.4253295,0.08088329,0.000007821342,0.0001134422],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.636625,0.0000608244,0.3574763,0.001354812,0.000376419,0.0001812508,0.000001992926,0.00006748278,0.003855912],"genre_scores_gemma":[0.96503,0.00001501387,0.03468015,0.00006620808,0.00005103225,0.000003853735,2.610631e-7,0.00001100798,0.0001425281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.674528,"threshold_uncertainty_score":0.6273102,"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."}}