{"id":"W3174272772","doi":"10.18653/v1/2021.findings-acl.170","title":"An Evaluation of Disentangled Representation Learning for Texts","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute","keywords":"Computer science; Representation (politics); Natural language processing; ENCODE; Task (project management); Artificial intelligence; Style (visual arts); Context (archaeology); Feature learning; Natural language understanding; Transfer of learning; Natural language; Machine learning","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":[0.01056895,0.002719207,0.001322741,0.002170422,0.000850165,0.002023908,0.002937292,0.003579355,0.003060879],"category_scores_gemma":[0.03402095,0.0004121348,0.001434065,0.001835097,0.001383142,0.005884066,0.002724856,0.00403678,0.001767909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001681163,"about_ca_system_score_gemma":0.001225542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004258775,"about_ca_topic_score_gemma":0.005598137,"domain_scores_codex":[0.993987,0.003266661,0.0003203339,0.001414057,0.0008000383,0.0002119601],"domain_scores_gemma":[0.9829359,0.01165366,0.0006726054,0.002679629,0.001478261,0.0005799606],"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":[0.003423179,0.002402458,0.007540839,0.001706577,0.000881476,0.0003532912,0.0004380782,0.4229143,0.01692576,0.006509404,0.02897177,0.5079329],"study_design_scores_gemma":[0.0002175512,0.0007740311,0.001844154,0.00008607981,0.00008159617,0.0001356454,0.0001299517,0.9780371,0.009407699,0.00582334,0.00342935,0.00003354489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5483218,0.01076691,0.3915841,0.003990187,0.001081318,0.001285923,0.0099663,0.01794461,0.01505884],"genre_scores_gemma":[0.7231762,0.001671223,0.2277105,0.0009656308,0.0003652587,0.0007692493,0.03762279,0.0009680651,0.006751081],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01056895,"threshold_uncertainty_score":0.05589461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09035460583850222,"score_gpt":0.3785722752602529,"score_spread":0.2882176694217506,"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."}}