{"id":"W1968267429","doi":"10.1177/0023830913484896","title":"Sidestepping the Combinatorial Explosion: An Explanation of <i>n</i> -gram Frequency Effects Based on Naive Discriminative Learning","year":2013,"lang":"en","type":"article","venue":"Language and Speech","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alexander von Humboldt-Stiftung","keywords":"Discriminative model; Word lists by frequency; Word (group theory); Natural language processing; Computer science; Artificial intelligence; Frequency; n-gram; Key (lock); Speech recognition; Linguistics; Language model; Mathematics; Statistics","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":[0.002270319,0.0008166459,0.00117192,0.00141871,0.001158179,0.002134522,0.002707932,0.00142894,0.01092327],"category_scores_gemma":[0.01830307,0.000915873,0.001595751,0.00134535,0.004306545,0.006930252,0.002728334,0.003359716,0.001541071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001240836,"about_ca_system_score_gemma":0.0006837226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00325019,"about_ca_topic_score_gemma":0.003404767,"domain_scores_codex":[0.9987606,0.0003894547,0.00006399886,0.0003540899,0.0002812517,0.0001506601],"domain_scores_gemma":[0.9915836,0.005480412,0.0005032925,0.00170351,0.0005234997,0.0002055536],"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":[0.0009542126,0.0003529109,0.01721986,0.0004448621,0.0002166867,0.001540441,0.001631344,0.1224234,0.01411339,0.6192797,0.01093323,0.21089],"study_design_scores_gemma":[0.00005544075,0.00008649309,0.002478905,0.00002476831,0.00003337336,0.0004483383,0.00007298523,0.3807488,0.001928851,0.612345,0.00173025,0.00004675931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1347792,0.0007547232,0.839725,0.003455193,0.0002072892,0.0001026596,0.0005156094,0.001368021,0.01909219],"genre_scores_gemma":[0.9091408,0.0004365821,0.08122322,0.001304967,0.0001938049,0.0001824701,0.0005712191,0.0005777789,0.00636915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01092327,"threshold_uncertainty_score":0.03654194,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007765609616439314,"score_gpt":0.2491088594124336,"score_spread":0.2413432497959943,"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."}}