{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001391575,0.001425833,0.0006555517,0.003539092,0.002434782,0.001963451,0.001576084,0.0008580184,0.0275677],"category_scores_gemma":[0.004974036,0.0003561121,0.0003428818,0.005104829,0.0008062538,0.001399556,0.002854362,0.0009260446,0.01244512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002219176,"about_ca_system_score_gemma":0.005622915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.3142273,"about_ca_topic_score_gemma":0.3341503,"domain_scores_codex":[0.9991183,0.0002756794,0.0001224205,0.000185925,0.0001741074,0.0001235189],"domain_scores_gemma":[0.9968488,0.0008655189,0.0001343857,0.0006106595,0.001190614,0.0003500379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0006668362,0.0001830906,0.01219819,0.002952089,0.0001335012,0.001272481,0.004516386,0.001009434,0.007871588,0.003547505,0.9064352,0.05921372],"study_design_scores_gemma":[0.0003205184,0.000080318,0.1334359,0.0006380258,0.0001746118,0.000729436,0.007368909,0.002954089,0.005509465,0.001372629,0.8472763,0.0001397836],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.06250612,0.0008655821,0.002501471,0.000568067,0.0002463208,0.0005237781,0.9047052,0.001624075,0.02645947],"genre_scores_gemma":[0.05528621,0.0002326421,0.003505838,0.00009381626,0.00002723094,0.001137218,0.9311336,0.0003781524,0.008205255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3142273,"threshold_uncertainty_score":0.6247966,"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."}}