{"id":"W2251404283","doi":"10.63317/3o7gcvqkiaid","title":"Morphological parsing of Swahili using crowdsourced lexical resources","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Swahili; Computer science; Parsing; Natural language processing; Artificial intelligence; Resource (disambiguation); Declaration; Lexical analysis; World Wide Web; Linguistics; Programming language","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":[0.0004356492,0.0001096709,0.0001923093,0.00009098024,0.00008485285,0.00008603957,0.000804283,0.0001049826,0.00002365176],"category_scores_gemma":[0.0001940759,0.00007997252,0.0000611206,0.0002822026,0.0001222286,0.0002173046,0.0003422613,0.0001534156,0.000003759706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001996392,"about_ca_system_score_gemma":0.00001408776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004859583,"about_ca_topic_score_gemma":0.00000101945,"domain_scores_codex":[0.9989053,0.0001003983,0.000229861,0.0002951144,0.0002450314,0.000224274],"domain_scores_gemma":[0.9992441,0.0001256036,0.00009952445,0.0004004542,0.00006591501,0.0000644094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003280109,0.0001834142,0.002256951,0.00008014102,0.0000204613,0.0000513828,0.0014819,0.0001722455,0.5749803,0.2949927,0.0006762607,0.1250714],"study_design_scores_gemma":[0.00039315,0.0002942591,0.0007196782,0.0001492742,0.00001436366,0.0002509125,0.00004594565,0.3096681,0.5679509,0.1179314,0.002041534,0.0005405702],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.26342,0.0001875445,0.7343473,0.0002399956,0.00003813243,0.00004179542,1.64914e-7,0.0004041307,0.001320915],"genre_scores_gemma":[0.5431435,3.909586e-7,0.4565873,0.0001995816,0.00002705103,5.973039e-7,1.668844e-7,0.000003471074,0.00003788348],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3094958,"threshold_uncertainty_score":0.3261185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02418380819301267,"score_gpt":0.2815513555588706,"score_spread":0.2573675473658579,"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."}}