{"id":"W1976965564","doi":"10.7202/1008337ar","title":"A Cognitive Model of Chinese Word Segmentation for Machine Translation","year":2012,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine translation; Computer science; Natural language processing; Text segmentation; Sentence; Artificial intelligence; Word (group theory); Segmentation; Bottleneck; Language translation; Translation (biology); Perspective (graphical); 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":[0.0011265,0.0007839159,0.0003527247,0.001545828,0.00135397,0.00278044,0.001446668,0.001004657,0.00548867],"category_scores_gemma":[0.003142183,0.0003600346,0.001642685,0.0015154,0.002992031,0.004730863,0.001346253,0.001140464,0.0007813199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00259817,"about_ca_system_score_gemma":0.00279549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01277023,"about_ca_topic_score_gemma":0.008522944,"domain_scores_codex":[0.999402,0.0002127246,0.00003211048,0.0001634105,0.0001115327,0.00007811458],"domain_scores_gemma":[0.9988656,0.0006052808,0.0001172417,0.0001142423,0.0001993788,0.00009821891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00011454,0.0001395177,0.003075134,0.0002812481,0.0001060208,0.0006212793,0.008252461,0.02704553,0.003815511,0.8923429,0.002971397,0.06123442],"study_design_scores_gemma":[0.00006611732,0.00009093786,0.002838862,0.0000624977,0.00009863221,0.0003301975,0.001274229,0.240982,0.001592994,0.7444385,0.008160586,0.00006445539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.134179,0.001060722,0.7502899,0.004755029,0.0002086895,0.000289736,0.0004163064,0.0006710293,0.1081295],"genre_scores_gemma":[0.8632947,0.0004236235,0.1269398,0.000371112,0.00008023135,0.0003366093,0.0002903029,0.00006023756,0.008203241],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01277023,"threshold_uncertainty_score":0.02539182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05449760028149134,"score_gpt":0.3269029220178653,"score_spread":0.2724053217363739,"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."}}