{"id":"W2060864821","doi":"10.1300/j104v32n03_08","title":"Word Division in the Transcription of Chinese Script in the Title Fields of Bibliographic Records","year":2001,"lang":"en","type":"article","venue":"Cataloging & Classification Quarterly","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Pinyin; Computer science; Ambiguity; Natural language processing; Information retrieval; Word (group theory); Transcription (linguistics); Orthography; Linguistics; Artificial intelligence; Chinese characters","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":[0.0005526933,0.00005626438,0.00007638044,0.0005392636,0.00002376383,0.00003994451,0.0006658204,0.00004929149,0.000004061164],"category_scores_gemma":[0.00001928905,0.00003275938,0.00003474667,0.002421741,0.0000407607,0.0002228344,0.000006556428,0.0001398529,0.000003432175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007576181,"about_ca_system_score_gemma":0.000012741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001187715,"about_ca_topic_score_gemma":0.000105965,"domain_scores_codex":[0.9993469,0.00009021445,0.0002024481,0.0001243035,0.0001565365,0.00007957881],"domain_scores_gemma":[0.9994235,0.00007423892,0.00009396266,0.0003662269,0.0000351758,0.000006886583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002510935,0.0003926926,0.0336312,0.0001115274,0.000007627665,0.00001400129,0.04476234,0.000004266502,0.03761497,0.0485735,0.003366256,0.8314965],"study_design_scores_gemma":[0.0007799023,0.0005643927,0.7770856,0.0003678064,0.00001313167,0.00004243875,0.003112432,0.01853518,0.001527076,0.193982,0.00355675,0.0004333298],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6578029,0.001556355,0.3346274,0.003157066,0.0002378809,0.0003339599,0.000002914067,0.0001047182,0.002176784],"genre_scores_gemma":[0.9968139,0.00003415957,0.003009581,0.00008544303,0.00001195795,0.00001552276,0.000009428451,0.000002408922,0.00001758515],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8310632,"threshold_uncertainty_score":0.1335889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02613999809245618,"score_gpt":0.287983754464532,"score_spread":0.2618437563720759,"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."}}