{"id":"W3032025286","doi":"","title":"Cifu: a Frequency Lexicon of Hong Kong Cantonese.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Linguistic Variation and Morphology","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Lexicon; Computer science; Lexical database; Word lists by frequency; Natural language processing; Lexical diversity; Artificial intelligence; Linguistics; Word (group theory); Phonology; Speech recognition; Vocabulary","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":[0.0007191608,0.00004345992,0.00009163577,0.00002725933,0.0001111653,0.00002132361,0.00006186598,0.00005370418,0.0007047836],"category_scores_gemma":[0.001126304,0.00004013977,0.00002088575,0.0001244393,0.00007306888,0.00003936382,0.00001550125,0.00004366959,0.000007407312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001824902,"about_ca_system_score_gemma":0.00008500501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005405897,"about_ca_topic_score_gemma":0.001148505,"domain_scores_codex":[0.9991596,0.0002062268,0.0001299197,0.0001180379,0.0002844904,0.0001017154],"domain_scores_gemma":[0.9996209,0.00006411186,0.00008758479,0.00005460763,0.00009988269,0.00007288162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003629018,0.00003418645,0.03218976,0.0000608727,0.00003861334,0.00001183418,0.8633214,0.00006005712,0.01415141,0.04181497,0.0004674497,0.04781317],"study_design_scores_gemma":[0.007767535,0.0009131889,0.3035026,0.0002540165,0.0008329482,0.00001362141,0.5191343,0.05179376,0.004616823,0.02074374,0.08894236,0.001485204],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9654391,0.0008908827,0.0001653545,0.002961616,0.00009270228,0.0001668087,0.000004978011,0.00002702562,0.03025153],"genre_scores_gemma":[0.998826,0.00003903075,0.0003119969,0.0003371142,0.0003528328,0.000004669628,0.000009114796,0.000003888848,0.0001153642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3441871,"threshold_uncertainty_score":0.8172135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0484546324202565,"score_gpt":0.3496756248661653,"score_spread":0.3012209924459088,"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."}}