{"id":"W3029614628","doi":"","title":"CantoMap: a Hong Kong Cantonese MapTask Corpus.","year":2020,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Geographic Information Systems Studies","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Transcription (linguistics); Computer science; Utterance; Annotation; Natural language processing; Phonetic transcription; Phonology; Artificial intelligence; Task (project management); Speech recognition; Linguistics; Engineering","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":[0.001157449,0.00007861167,0.0001224178,0.00005574935,0.0004635167,0.0001078404,0.00008583909,0.00005322284,0.0001486259],"category_scores_gemma":[0.000301626,0.00006986825,0.00003301181,0.0003009514,0.000104607,0.0001748315,0.00003863443,0.00006046378,0.00003435673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003358179,"about_ca_system_score_gemma":0.00004337935,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01271558,"about_ca_topic_score_gemma":0.006530082,"domain_scores_codex":[0.9986573,0.0001709338,0.0001833764,0.0001365515,0.00066043,0.0001913394],"domain_scores_gemma":[0.9994912,0.00005716688,0.0001125469,0.00007753196,0.0001457983,0.000115741],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001903634,0.00000753221,0.02717495,0.00004988758,0.00003864629,0.000004847843,0.9121115,0.00004548147,0.0001805891,0.001206886,0.0009166814,0.05824395],"study_design_scores_gemma":[0.001543783,0.0001015695,0.1103433,0.00008410485,0.0001287219,0.000005368853,0.7005152,0.01277615,0.00005523948,0.0002328583,0.1737734,0.0004403228],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9603944,0.002368001,0.00003746957,0.003576588,0.0001015843,0.0003812645,0.000007721489,0.00008741,0.03304555],"genre_scores_gemma":[0.9987488,0.0001624277,0.00005313892,0.00041185,0.0003054084,0.00002530328,0.000009711624,0.000005405699,0.0002779851],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2115963,"threshold_uncertainty_score":0.9938588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03570656174926953,"score_gpt":0.3177618021598226,"score_spread":0.2820552404105531,"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."}}