{"id":"W3173783447","doi":"10.18653/v1/2021.acl-long.72","title":"DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":362,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; Vector Institute; University of Toronto","funders":"National Institutes of Health; Compute Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Natural language processing; Artificial intelligence; Linguistics; Computational linguistics; Volume (thermodynamics); Association (psychology); Joint (building); Deep learning; Cognitive science; Psychology; Philosophy; Epistemology; Engineering","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":[0.000115329,0.00006563251,0.00009494663,0.00003137834,0.0001553482,0.0001191049,0.0002440382,0.00003163768,0.00006876882],"category_scores_gemma":[0.0003093418,0.00006465057,0.00005774858,0.0001636062,0.00001292157,0.0002331882,0.0001315595,0.00007863875,0.00002160917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001897838,"about_ca_system_score_gemma":0.00008495597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248217,"about_ca_topic_score_gemma":0.00004690413,"domain_scores_codex":[0.9991567,0.00004865799,0.0001518245,0.0003345462,0.000119965,0.0001882673],"domain_scores_gemma":[0.9991003,0.0003490103,0.00002687143,0.0002709287,0.000192334,0.00006055795],"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":[0.000007944257,0.0000841983,0.003624944,0.00001729361,0.00006428767,0.00003284837,0.003200199,0.03632082,0.004907124,0.7841054,0.0006581229,0.1669768],"study_design_scores_gemma":[0.0005136149,0.00002165032,0.001009198,0.000005416894,0.000005666585,0.00001164183,0.0008706595,0.9862226,0.004417546,0.004321765,0.002492006,0.0001082709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005379884,0.00007804373,0.9833972,0.001362418,0.0001227704,0.0001186799,5.22453e-7,0.0001494933,0.009390983],"genre_scores_gemma":[0.6778063,0.00000444527,0.3192238,0.0003937726,0.00006365338,0.00002972403,0.000006023133,0.000005271088,0.00246696],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9499018,"threshold_uncertainty_score":0.2636374,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03108129907966992,"score_gpt":0.2870895336430146,"score_spread":0.2560082345633448,"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."}}