{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005807996,0.0001857846,0.0001343181,0.0001314527,0.0003488935,0.0001416267,0.0006754642,0.00005992806,0.000006038042],"category_scores_gemma":[3.833837e-7,0.0001884848,0.0001119562,0.0006013488,0.00001711206,0.0003474947,0.000145765,0.0000771038,0.00005005753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007588294,"about_ca_system_score_gemma":0.00007205694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002877779,"about_ca_topic_score_gemma":0.00000616004,"domain_scores_codex":[0.9987547,0.00001107026,0.0003285583,0.0005244268,0.000150792,0.0002304213],"domain_scores_gemma":[0.9990945,0.0001024234,0.00013729,0.0003966523,0.0001864509,0.00008268299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001630258,0.00008178952,0.00002488854,0.000006764637,0.00000775455,1.864379e-7,0.00002599998,0.0008458738,0.01050179,0.82853,0.007498768,0.1524745],"study_design_scores_gemma":[0.0003439004,0.00002234741,0.0007303956,0.000004661716,0.00000667625,0.00002074417,0.000002169905,0.02312489,0.00479531,0.8030517,0.1676727,0.0002245093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002309378,0.00004627664,0.9942652,0.002617049,0.00002764145,0.001548111,0.00002162054,0.0007386962,0.000504465],"genre_scores_gemma":[0.01236648,0.000005902651,0.9825823,0.0007882765,0.0005021747,0.002815663,0.0001877344,0.00002079425,0.0007306263],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1601739,"threshold_uncertainty_score":0.7686188,"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."}}