{"id":"W3162734203","doi":"10.18653/v1/2021.findings-acl.84","title":"A Survey of Data Augmentation Approaches for NLP","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Popularity; Artificial intelligence; Data science; Natural language processing; Resource (disambiguation); Labeled data; Machine learning; Information retrieval","routes":{"ca_aff":true,"ca_fund":false,"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":[0.006272862,0.002342331,0.002390667,0.005542469,0.001469843,0.00383484,0.003476076,0.00248974,0.007733464],"category_scores_gemma":[0.02555768,0.001140109,0.002967241,0.007716773,0.001977342,0.006840107,0.004537645,0.004307011,0.005473488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00140169,"about_ca_system_score_gemma":0.00258449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004077883,"about_ca_topic_score_gemma":0.004465778,"domain_scores_codex":[0.9931145,0.003043045,0.0006312327,0.001553097,0.001494083,0.0001640786],"domain_scores_gemma":[0.9840911,0.01181165,0.0004349195,0.002207956,0.001291742,0.0001626396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001317892,0.0001261739,0.0009920911,0.003278181,0.0001991499,0.0001834433,0.0005291923,0.01734759,0.002804164,0.02003177,0.03505859,0.9193178],"study_design_scores_gemma":[0.00008191313,0.0002544955,0.002667333,0.00324732,0.0002639515,0.001171967,0.001157988,0.2955868,0.01251408,0.1805223,0.5023062,0.0002255521],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.0027214,0.04757282,0.9279507,0.003642652,0.0006694893,0.0003240469,0.003364791,0.006002245,0.007752001],"genre_scores_gemma":[0.06988317,0.07752369,0.8173912,0.002909572,0.002223541,0.001820348,0.01832747,0.002163746,0.007757228],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.007733464,"threshold_uncertainty_score":0.03317451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5270259338359118,"score_gpt":0.3715261320235383,"score_spread":0.1554998018123735,"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."}}