{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002398779,0.001712398,0.001277387,0.00052997,0.0004573253,0.0008849343,0.001706141,0.001420129,0.002952362],"category_scores_gemma":[0.009880307,0.0005109532,0.0008559643,0.0005814154,0.002102223,0.002743329,0.002848625,0.00274975,0.001258288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006811292,"about_ca_system_score_gemma":0.0005812991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007427991,"about_ca_topic_score_gemma":0.000949601,"domain_scores_codex":[0.9987601,0.000542925,0.00007218083,0.0002920443,0.0002369275,0.00009591286],"domain_scores_gemma":[0.9948105,0.003647353,0.0003513762,0.000707453,0.0003559754,0.0001273302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000766985,0.0002774455,0.002471135,0.0004059671,0.0000991047,0.0004032746,0.0002977972,0.7521851,0.023954,0.02793911,0.009521735,0.1816784],"study_design_scores_gemma":[0.00002458156,0.00009596217,0.0001564686,0.00002095923,0.00001430227,0.00007289939,0.00001754146,0.9768797,0.006427346,0.01465198,0.001622723,0.00001550132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05119413,0.00081801,0.9414651,0.0008405366,0.0001951968,0.000191613,0.0003342354,0.001747343,0.003213939],"genre_scores_gemma":[0.7924888,0.0004645524,0.1959961,0.001004763,0.0002465747,0.0006077586,0.001156416,0.0002991594,0.007735882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002952362,"threshold_uncertainty_score":0.01268607,"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."}}