{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002673212,0.000137707,0.0001539677,0.00009126621,0.0001578573,0.0001578897,0.00043797,0.00007131785,0.000008450018],"category_scores_gemma":[0.0001908493,0.00008899168,0.00003301954,0.0002304795,0.00005570621,0.0006275987,0.00009042613,0.0002594508,0.000003945268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002290672,"about_ca_system_score_gemma":0.00002072479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000396095,"about_ca_topic_score_gemma":0.000007186834,"domain_scores_codex":[0.9989094,0.0002103113,0.0001526433,0.0002652113,0.0002927997,0.0001696741],"domain_scores_gemma":[0.9990447,0.0003487921,0.0001279782,0.0003220231,0.0001042155,0.0000523534],"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":[0.00002737541,0.0003017694,0.001062054,0.0002733803,0.00002549866,0.0001814131,0.03618043,0.00002403752,0.1763677,0.09331563,0.0002788759,0.6919618],"study_design_scores_gemma":[0.001069938,0.001585735,0.001390148,0.0005432066,0.00002850963,0.00002484469,0.003251613,0.04552898,0.8722731,0.07374838,0.0000334459,0.0005221023],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8925338,0.0014829,0.1013954,0.001026977,0.0003945266,0.0008680049,0.000001836324,0.0005619616,0.001734577],"genre_scores_gemma":[0.9510077,0.000004918913,0.04852712,0.0002944396,0.00008178278,0.00004208879,0.000007882733,0.000009509719,0.00002458244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6959054,"threshold_uncertainty_score":0.3628975,"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."}}