{"id":"W4378446370","doi":"10.48550/arxiv.2305.13658","title":"Understanding Compositional Data Augmentation in Typologically Diverse Morphological Inflection","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spurious relationship; Morpheme; Computer science; Inflection; Generalization; Compositional data; Natural language processing; Phonology; Phonotactics; Artificial intelligence; Selection (genetic algorithm); Linguistics; Machine learning; Mathematics","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":[0.004859803,0.0008197918,0.0005954025,0.001467124,0.0006536673,0.002010221,0.001518657,0.00134008,0.001648249],"category_scores_gemma":[0.02042377,0.000497718,0.00105883,0.001367771,0.00146946,0.003296394,0.003006896,0.001952522,0.0009211681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004151272,"about_ca_system_score_gemma":0.0007489495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007830301,"about_ca_topic_score_gemma":0.002304593,"domain_scores_codex":[0.997911,0.001080954,0.0001291301,0.0005049063,0.0002950223,0.00007893387],"domain_scores_gemma":[0.9876223,0.008260868,0.0005573367,0.002633427,0.0007774898,0.0001485127],"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":[0.001146475,0.0005737251,0.04392566,0.0009970985,0.0003007382,0.0006943889,0.003388283,0.1143235,0.06505977,0.02069858,0.007345121,0.7415467],"study_design_scores_gemma":[0.00009861256,0.0003578723,0.01388897,0.0001765277,0.00011053,0.0007229468,0.001401544,0.8425342,0.04034338,0.08417173,0.01612368,0.00006983534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3548212,0.001475679,0.6339263,0.001052731,0.0001222648,0.0001669963,0.001668197,0.003614689,0.003151989],"genre_scores_gemma":[0.6335627,0.000354681,0.3591388,0.0002806053,0.00006428264,0.0002723362,0.005004337,0.0002887808,0.001033529],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004859803,"threshold_uncertainty_score":0.0257014,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4774692118771993,"score_gpt":0.284890306832388,"score_spread":0.1925789050448113,"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."}}