{"id":"W4389523818","doi":"10.18653/v1/2023.findings-emnlp.788","title":"Do “English” Named Entity Recognizers Work Well on Global Englishes?","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Natural language processing; Named-entity recognition; Named entity; Transformer; Test (biology); Training set; Test data; Botany","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":[0.005741962,0.002342227,0.001604441,0.001958336,0.0008079162,0.002848593,0.001303523,0.00171554,0.005224988],"category_scores_gemma":[0.01259729,0.0005670149,0.001610028,0.002200241,0.0008149263,0.0103703,0.001600939,0.001847516,0.01005809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005869662,"about_ca_system_score_gemma":0.0008021921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01393242,"about_ca_topic_score_gemma":0.03833819,"domain_scores_codex":[0.99727,0.000734397,0.0001655362,0.00125005,0.0002624591,0.0003175235],"domain_scores_gemma":[0.9955787,0.001710679,0.00020444,0.001549978,0.0007255117,0.0002305613],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0015782,0.0005905629,0.1084204,0.001562594,0.001858615,0.001022619,0.001615898,0.04080081,0.03166671,0.003990375,0.08631001,0.7205833],"study_design_scores_gemma":[0.0004348053,0.002422686,0.1728744,0.001393173,0.002887156,0.003200332,0.01132148,0.4700673,0.1033325,0.02312255,0.2083375,0.0006062319],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6892061,0.01142808,0.1721707,0.006380021,0.001909965,0.0004086236,0.01909938,0.02485076,0.07454641],"genre_scores_gemma":[0.8765482,0.003062689,0.05712051,0.001534567,0.0003473423,0.0001105766,0.04122766,0.002239013,0.01780947],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01393242,"threshold_uncertainty_score":0.03036678,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04899524873901231,"score_gpt":0.2751326913912673,"score_spread":0.226137442652255,"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."}}