{"id":"W2021856631","doi":"10.7202/019244ar","title":"New Light Shed on Chinese Word Segmentation in MT by a Language Investigation","year":2008,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Machine translation; Word (group theory); Artificial intelligence; Text segmentation; Feature (linguistics); Segmentation; Linguistics; Translation (biology); Space (punctuation); Chinese language","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":[0.01422531,0.0008052353,0.0007761894,0.003235368,0.005622753,0.006123936,0.0009789981,0.002331452,0.004463194],"category_scores_gemma":[0.02053615,0.0005247456,0.0005857786,0.006613109,0.01980342,0.02764614,0.004443272,0.002873793,0.0002645759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005300929,"about_ca_system_score_gemma":0.005859189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01590929,"about_ca_topic_score_gemma":0.02016409,"domain_scores_codex":[0.9929748,0.005075128,0.0002792997,0.0005106917,0.0005981423,0.0005619911],"domain_scores_gemma":[0.9612259,0.03278469,0.001480445,0.002105387,0.001663009,0.000740514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002369881,0.0001229801,0.01363593,0.0006197306,0.00003013715,0.001782719,0.1417332,0.0008364636,0.002831109,0.6965631,0.005595976,0.1360117],"study_design_scores_gemma":[0.00004072333,0.0001658315,0.02716263,0.001594107,0.00006137843,0.00131246,0.2793109,0.007088123,0.004199314,0.5550096,0.1239306,0.0001243398],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5715231,0.03659743,0.07635434,0.1563556,0.0009552356,0.0001890433,0.0002901365,0.0001361292,0.157599],"genre_scores_gemma":[0.9800431,0.005362326,0.008112252,0.002124214,0.0004318864,0.0001227057,0.00007501261,0.00005521491,0.00367343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01590929,"threshold_uncertainty_score":0.07523155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01883900437247245,"score_gpt":0.271211043192125,"score_spread":0.2523720388196526,"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."}}