{"id":"W2386177573","doi":"","title":"A New Dictionary Mechanism for Chinese Word Segmentation","year":2006,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Segmentation; Search engine indexing; Mechanism (biology); Hash function; Character (mathematics); Artificial intelligence; Word (group theory); Component (thermodynamics); Natural language processing; Text segmentation; Speech recognition; Pattern recognition (psychology); Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008684943,0.0006275935,0.001206064,0.001951896,0.001568849,0.001458625,0.00183285,0.000828321,0.008600817],"category_scores_gemma":[0.002713631,0.0005267998,0.000545188,0.00301454,0.001226468,0.006013521,0.002610904,0.0008589632,0.002774961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007599153,"about_ca_system_score_gemma":0.001761811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001937456,"about_ca_topic_score_gemma":0.002007382,"domain_scores_codex":[0.9990006,0.000128867,0.0001702861,0.0002827621,0.0002893798,0.0001280742],"domain_scores_gemma":[0.9978006,0.0003835917,0.0001556564,0.0007988057,0.0007207035,0.0001405174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009881078,0.0001670295,0.002298167,0.0008429111,0.00009547744,0.0003694589,0.001090889,0.005784175,0.1232288,0.1275706,0.02277252,0.7147918],"study_design_scores_gemma":[0.0006210677,0.001261182,0.002303783,0.000169407,0.000377318,0.002319013,0.0005699055,0.2798967,0.345467,0.09513874,0.2713653,0.0005106423],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02961418,0.001370401,0.9483383,0.0002800908,0.0005451951,0.0003506628,0.0006316074,0.01144262,0.007426897],"genre_scores_gemma":[0.3468641,0.0009917985,0.6337437,0.0004997028,0.0004977924,0.0006145872,0.002207125,0.001076897,0.01350429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008600817,"threshold_uncertainty_score":0.02877265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006470361364399376,"score_gpt":0.2662634473596081,"score_spread":0.2597930859952087,"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."}}