{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006521712,0.000548744,0.000553528,0.0007728616,0.0003441728,0.0008008573,0.002692451,0.0002350647,0.00009427762],"category_scores_gemma":[0.00004200253,0.0004603328,0.0002064595,0.001272369,0.0002451794,0.0009360268,0.001114003,0.0005642322,0.00007736247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002815165,"about_ca_system_score_gemma":0.0002613739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002606954,"about_ca_topic_score_gemma":0.00009081448,"domain_scores_codex":[0.9963497,0.00002948279,0.0005769106,0.001431128,0.0009740104,0.0006387589],"domain_scores_gemma":[0.9978528,0.0002166226,0.0003140814,0.001216351,0.0002197643,0.0001803754],"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":[0.000003124343,0.00002610141,0.000231813,0.00002647951,0.00002182597,0.00007613394,0.0009149368,0.01334636,0.00006581541,0.003664923,0.000009842121,0.9816126],"study_design_scores_gemma":[0.000232742,0.00009307702,0.0001551287,0.0001175892,0.000013857,0.0000703603,2.698987e-7,0.9569138,0.0001087713,0.04008472,0.001613292,0.0005963998],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002960405,0.0003808086,0.9863779,0.0004494157,0.0009321837,0.0002783538,0.000002156126,0.0002628845,0.01102026],"genre_scores_gemma":[0.04793732,0.0001355061,0.9493151,0.001017575,0.0007523472,0.000009269328,0.00001335581,0.0000443493,0.0007751653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9810162,"threshold_uncertainty_score":0.9997848,"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."}}