{"id":"W1586407478","doi":"10.1007/3-540-44816-0_24","title":"Self-Supervised Chinese Word Segmentation","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Natural language processing; Artificial intelligence; Computer science; Word (group theory); Text segmentation; Segmentation; Linguistics; Philosophy","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":[0.0007945267,0.001448358,0.001350294,0.002526819,0.001018005,0.00141656,0.001295983,0.001086393,0.01108736],"category_scores_gemma":[0.001802241,0.0004963162,0.001055444,0.002737464,0.0006812211,0.00203031,0.001292103,0.0009520825,0.009870516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005312663,"about_ca_system_score_gemma":0.001604646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004779294,"about_ca_topic_score_gemma":0.008878561,"domain_scores_codex":[0.9990367,0.0001479437,0.00008302144,0.0004631328,0.0001455386,0.0001236991],"domain_scores_gemma":[0.9987148,0.0003944952,0.00006509106,0.0002415778,0.0005088053,0.00007521214],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004008185,0.0001186829,0.001516144,0.0003145926,0.00009252851,0.0002014483,0.0001748233,0.006502296,0.04463979,0.002702201,0.02303748,0.9202991],"study_design_scores_gemma":[0.00009335087,0.0003180761,0.007968628,0.00008823175,0.0002773121,0.0008582153,0.0004654666,0.8189136,0.1190528,0.01318523,0.0386874,0.00009166516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.132256,0.003796895,0.8049629,0.0006064267,0.001101396,0.000508241,0.00445264,0.02768412,0.02463151],"genre_scores_gemma":[0.4598994,0.001075199,0.4698083,0.0004344835,0.0006051924,0.0003934079,0.0205765,0.002583153,0.04462441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01108736,"threshold_uncertainty_score":0.0370909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01228191426832061,"score_gpt":0.2324298831829698,"score_spread":0.2201479689146492,"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."}}