{"id":"W2135032142","doi":"10.5539/ijel.v2n6p27","title":"Transitional Probability and Word Segmentation","year":2012,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Language Development and Disorders","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Word (group theory); Segmentation; Text segmentation; Computer science; Artificial intelligence; Computation; Natural language processing; Statistical learning; Probability distribution; Linguistics; Mathematics; Statistics; Algorithm","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":[0.0005945581,0.0001902796,0.0002751794,0.001131148,0.0004690615,0.002031051,0.0003729999,0.0004247451,0.005895136],"category_scores_gemma":[0.009742317,0.0001819451,0.0002529882,0.001203575,0.001894323,0.00306686,0.001270085,0.0006576746,0.0004915623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005027486,"about_ca_system_score_gemma":0.0006799514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001138524,"about_ca_topic_score_gemma":0.0007163634,"domain_scores_codex":[0.999449,0.0001539604,0.00004909539,0.00015328,0.0001293531,0.00006530149],"domain_scores_gemma":[0.994971,0.003464085,0.000703785,0.0001988546,0.0004082758,0.0002538945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001132511,0.0001807776,0.07834484,0.0006562439,0.0001437222,0.001485565,0.0104613,0.009286301,0.01788413,0.5727701,0.00145512,0.3061994],"study_design_scores_gemma":[0.00003082326,0.0003324142,0.1846097,0.0001585389,0.00008854088,0.001730358,0.002933957,0.01884615,0.004844349,0.7775039,0.008831193,0.00009013758],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8340639,0.00530318,0.09111565,0.0009818535,0.0001465166,0.00005724062,0.0003322941,0.000278113,0.06772108],"genre_scores_gemma":[0.9936572,0.0005944671,0.004326405,0.00004474238,0.00004174654,0.00001552914,0.00009324827,0.00002882208,0.001197932],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005895136,"threshold_uncertainty_score":0.01972121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02026763445237813,"score_gpt":0.3153563173588409,"score_spread":0.2950886829064628,"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."}}