{"id":"W2914344421","doi":"10.1002/pra2.2018.14505501004","title":"A word‐level language identification strategy for resource‐scarce languages","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Yoruba; Trigram; Natural language processing; Artificial intelligence; Igbo; Language identification; Hausa; Word (group theory); Identification (biology); Character (mathematics); Natural language; Linguistics; 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":[0.001794364,0.00007776345,0.0001049051,0.0004976175,0.0004217733,0.0003230796,0.001212635,0.0001199818,3.246541e-7],"category_scores_gemma":[0.003105117,0.00005903914,0.00002916455,0.001830548,0.0002619188,0.002815458,0.0002599363,0.00008076334,0.000001632629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001435114,"about_ca_system_score_gemma":0.00009090645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005180176,"about_ca_topic_score_gemma":0.000002400309,"domain_scores_codex":[0.9989136,0.000002257019,0.0002904056,0.0001713178,0.0003996161,0.0002228192],"domain_scores_gemma":[0.9965626,0.00005875406,0.0006960736,0.000148289,0.002511627,0.00002267873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001058377,0.00001365806,0.001245996,0.00008493356,0.00001070951,7.793616e-9,0.003263272,2.382665e-7,0.09470968,0.7480866,0.00281188,0.1497625],"study_design_scores_gemma":[0.0003729908,0.0001299742,0.001501582,0.00004037822,0.00001370672,0.000005714113,0.002613821,0.003406212,0.912437,0.07055512,0.008764252,0.0001592228],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6252791,0.000806621,0.298899,0.04816776,0.0008597769,0.006643882,0.000233131,0.003359836,0.01575087],"genre_scores_gemma":[0.9572203,0.000002832218,0.04218563,0.0001832479,0.00002934688,0.00008678154,0.000002251289,0.000003182964,0.0002864668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8177273,"threshold_uncertainty_score":0.3717339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01446866564535378,"score_gpt":0.2930967782731784,"score_spread":0.2786281126278246,"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."}}