{"id":"W1513008738","doi":"10.1007/978-3-642-01818-3_15","title":"Training Global Linear Models for Chinese Word Segmentation","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Margin (machine learning); Segmentation; Word (group theory); Sentence; Artificial intelligence; Perceptron; Pattern recognition (psychology); Text segmentation; Linear model; Natural language processing; Speech recognition; Artificial neural network; Machine learning; Mathematics","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":[0.001341999,0.003084097,0.002123073,0.001576518,0.0009597551,0.001353669,0.002157393,0.002207263,0.009756326],"category_scores_gemma":[0.002955042,0.001534898,0.001825546,0.002578299,0.0007066163,0.002578269,0.001775013,0.003587759,0.005645277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156664,"about_ca_system_score_gemma":0.001843819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02004873,"about_ca_topic_score_gemma":0.03426552,"domain_scores_codex":[0.9992839,0.0001797133,0.00004559826,0.0003123496,0.0000585482,0.0001200163],"domain_scores_gemma":[0.9980997,0.001337639,0.00006159583,0.0001795795,0.0002377105,0.00008368226],"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":[0.0008101602,0.0002083855,0.001548584,0.0002681857,0.0002390915,0.0001886763,0.0001619767,0.1837017,0.00873025,0.002625253,0.02048042,0.7810373],"study_design_scores_gemma":[0.00003128276,0.00007170111,0.0003311997,0.00001231845,0.00004633723,0.00002313462,0.00005022069,0.9927109,0.002578069,0.003054309,0.00107737,0.00001311969],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1073308,0.005182937,0.8550294,0.0007875299,0.00056365,0.0001715814,0.002241435,0.02412328,0.004569479],"genre_scores_gemma":[0.5331113,0.001825767,0.4167411,0.0008678692,0.0005053816,0.000631555,0.01672912,0.002863343,0.02672447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02004873,"threshold_uncertainty_score":0.03986406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02675131427589033,"score_gpt":0.3085997165788049,"score_spread":0.2818484023029146,"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."}}