{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004654049,0.00008120482,0.00009447798,0.00005938035,0.0004997649,0.0001891823,0.001039529,0.0000155781,0.000008250519],"category_scores_gemma":[0.0001960201,0.00006938124,0.00001199532,0.0001809673,0.00002496752,0.0006319243,0.001602134,0.0003193868,3.208318e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002523614,"about_ca_system_score_gemma":0.00004748921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000202974,"about_ca_topic_score_gemma":0.000004215343,"domain_scores_codex":[0.9991413,0.00005281085,0.00009431136,0.0003761497,0.0001583043,0.0001771476],"domain_scores_gemma":[0.9994703,0.0001305008,0.00006425236,0.0002650926,0.00004061002,0.00002925273],"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":[0.00001365505,0.00001549237,0.00007677954,0.00003599092,0.000006948462,0.00001407427,0.002430334,0.000005478782,0.003458712,0.005141776,0.001049172,0.9877516],"study_design_scores_gemma":[0.0003125245,0.00009458957,0.00003871187,0.00001264829,0.000006696725,0.00007910302,0.001145678,0.9882646,0.002019114,0.002104269,0.00570934,0.0002127678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002237644,0.02211324,0.9734593,0.0008165567,0.00008923733,0.0002336067,0.000008428774,0.000793057,0.0002489229],"genre_scores_gemma":[0.6345072,0.000001147867,0.3645414,0.0003179591,0.00002163143,0.00002444613,0.00002269447,0.000005538047,0.0005579656],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9882591,"threshold_uncertainty_score":0.3843838,"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."}}