{"id":"W4382202705","doi":"10.1609/aaai.v37i11.26486","title":"Adversarial Word Dilution as Text Data Augmentation in Low-Resource Regime","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Benchmark (surveying); Word (group theory); Computer science; Mixing (physics); Embedding; Resource (disambiguation); Artificial intelligence; Adversarial system; Process (computing); Natural language processing; Word embedding; Class (philosophy); Machine learning; Data mining; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000939363,0.0001753328,0.0001954037,0.0002424269,0.0001371471,0.0002180564,0.003265443,0.0000916783,0.00003376059],"category_scores_gemma":[0.0006459146,0.0001496618,0.00005181549,0.001297785,0.0001252683,0.0008226498,0.001186231,0.0002791098,0.0003023398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007548733,"about_ca_system_score_gemma":0.0001214268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001644141,"about_ca_topic_score_gemma":0.00003695024,"domain_scores_codex":[0.9977924,0.00002738622,0.0005448847,0.0006931971,0.0005849604,0.0003571825],"domain_scores_gemma":[0.9986936,0.000107323,0.0002935871,0.0006544164,0.0001859614,0.0000650646],"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":[0.000118953,0.0001123595,0.0002480281,0.00005137662,0.00001154384,0.000002172734,0.00323431,0.001878229,0.01904448,0.7645514,0.0006074196,0.2101397],"study_design_scores_gemma":[0.00007250725,0.00006963546,0.0003899898,0.000380222,0.000007579002,0.000002781169,0.001160735,0.7808732,0.08783769,0.1286945,0.0002814493,0.0002296743],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8688679,0.00002560299,0.09266759,0.01887959,0.001668176,0.001303879,0.00001547267,0.0005208012,0.01605103],"genre_scores_gemma":[0.9977736,0.0000229951,0.001529209,0.0001672723,0.000107719,0.00001817369,0.000005045844,0.00001030537,0.0003656994],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.778995,"threshold_uncertainty_score":0.6103033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1281727623387476,"score_gpt":0.3286053743921488,"score_spread":0.2004326120534012,"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."}}