{"id":"W4385572818","doi":"10.18653/v1/2022.emnlp-main.128","title":"AfroLID: A Neural Language Identification Tool for African Languages","year":2022,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Advanced Micro Devices","keywords":"Computer science; Domain (mathematical analysis); Identification (biology); Natural language processing; Set (abstract data type); Cover (algebra); Artificial intelligence; Exploit; Language identification; Natural language; Programming language; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005149168,0.00005848493,0.00006514207,0.0000698093,0.0002741216,0.00009698238,0.0004845684,0.00001428603,0.0001725663],"category_scores_gemma":[0.00005730874,0.00005652727,0.00005268414,0.0002890346,0.000008691049,0.0001742427,0.0001957641,0.00008285142,0.00001963097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003699193,"about_ca_system_score_gemma":0.00002374693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002137157,"about_ca_topic_score_gemma":0.000003544656,"domain_scores_codex":[0.9992269,0.00008007815,0.000137132,0.0002153316,0.0001716245,0.0001689805],"domain_scores_gemma":[0.9995174,0.00008068575,0.00005797152,0.0002837695,0.00002740967,0.0000327048],"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":[0.00004888692,0.0001486147,0.001084474,0.00003925016,0.00003027946,0.0000274118,0.01739077,0.0007679117,0.03839868,0.7653927,0.01299917,0.1636719],"study_design_scores_gemma":[0.001726007,0.0004195362,0.01085391,0.00000490501,0.00003154983,0.0001083783,0.01755714,0.7912219,0.06783877,0.009466828,0.09965388,0.001117166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07384464,0.0001548711,0.9192773,0.00401754,0.0003930416,0.0003448036,0.00004153753,0.0003955186,0.001530824],"genre_scores_gemma":[0.9871379,3.493598e-7,0.007614113,0.0006166471,0.00004772858,0.0001493148,0.00003609845,0.000005027568,0.004392821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9132932,"threshold_uncertainty_score":0.2305115,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02260801631974186,"score_gpt":0.3036981982625557,"score_spread":0.2810901819428138,"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."}}