{"id":"W4287887329","doi":"10.18653/v1/2022.naacl-tutorials.6","title":"Contrastive Data and Learning for Natural Language Processing","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; Westlake University; University of Virginia; Pennsylvania State University; University of Pennsylvania","keywords":"Zhàng; Computer science; Computational linguistics; Natural language processing; Artificial intelligence; Language technology; Linguistics; Natural language; Human language; Programming language; Comprehension approach; China; History; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005366884,0.001109869,0.001310649,0.002826834,0.001175177,0.00333949,0.00258812,0.001392795,0.008552709],"category_scores_gemma":[0.01740214,0.001075957,0.001384063,0.002655747,0.002783383,0.008846021,0.003889589,0.004308745,0.004185959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001381418,"about_ca_system_score_gemma":0.001136887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00243681,"about_ca_topic_score_gemma":0.00579113,"domain_scores_codex":[0.9974748,0.001109093,0.0001975853,0.0006276456,0.0005066483,0.00008412397],"domain_scores_gemma":[0.9928039,0.004176361,0.0001888061,0.00201148,0.0006571212,0.0001623925],"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":[0.0003672917,0.0002243846,0.001724167,0.0005290585,0.0001672503,0.0001743618,0.0003898929,0.01197431,0.004391378,0.3963194,0.04016658,0.5435719],"study_design_scores_gemma":[0.00004005724,0.00005334253,0.0006329628,0.00008298454,0.00003270387,0.00009534053,0.0001311803,0.1947275,0.005146116,0.7565636,0.04245964,0.00003461435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004950142,0.003985847,0.9782391,0.00204172,0.000362335,0.0001161548,0.001051259,0.003293206,0.005960184],"genre_scores_gemma":[0.1276655,0.002314385,0.8566571,0.0005076514,0.0005574934,0.0006195059,0.003886707,0.0008357609,0.00695595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008552709,"threshold_uncertainty_score":0.02861166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01609528598964778,"score_gpt":0.2996274505530756,"score_spread":0.2835321645634278,"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."}}