{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001263041,0.001076832,0.0008876311,0.003989676,0.001170534,0.001691652,0.0009992531,0.0007184942,0.004015018],"category_scores_gemma":[0.005123226,0.0004937921,0.0005601563,0.001541312,0.0006701764,0.002699298,0.001867509,0.0008783432,0.00327827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005200365,"about_ca_system_score_gemma":0.001461376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002518436,"about_ca_topic_score_gemma":0.003616073,"domain_scores_codex":[0.9989554,0.0003702045,0.00009295848,0.0003401882,0.0001432212,0.00009791778],"domain_scores_gemma":[0.9968484,0.001459521,0.0003358436,0.0003617895,0.0008832727,0.000111129],"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":[0.0005619392,0.0004623358,0.01691212,0.0005161537,0.0001033958,0.001027192,0.003304327,0.009484167,0.1885051,0.008589737,0.003705776,0.7668277],"study_design_scores_gemma":[0.0001301847,0.0007366123,0.02223397,0.0001639648,0.0003747959,0.002496572,0.008762266,0.6373588,0.2770851,0.02604352,0.02439341,0.0002208076],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2265787,0.0002547119,0.761506,0.0004863007,0.00004374553,0.0003803341,0.0004843464,0.005243295,0.005022594],"genre_scores_gemma":[0.6094644,0.0001219213,0.3860575,0.0001656914,0.00002743447,0.0002520721,0.0007541376,0.0003275072,0.002829365],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004015018,"threshold_uncertainty_score":0.01343161,"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."}}