{"id":"W1604751532","doi":"10.1111/j.1467-9922.2010.00616.x","title":"Lexical Frequency Profiles and Zipf's Law","year":2010,"lang":"en","type":"article","venue":"Language Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Victoria","funders":"","keywords":"Zipf's law; Vocabulary; Word lists by frequency; Natural language processing; Artificial intelligence; Probabilistic logic; Word (group theory); Computer science; Homogeneous; Linguistics; Psychology; Statistics; Cognitive psychology; Statistical physics; Mathematics; Sentence","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":[0.003210115,0.0003873182,0.0009065774,0.003482747,0.0009772675,0.002456072,0.001385861,0.001516762,0.004004422],"category_scores_gemma":[0.04047421,0.0005110209,0.0006791963,0.002392787,0.002608886,0.006126281,0.0008933677,0.001260893,0.001217595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001906442,"about_ca_system_score_gemma":0.0006555058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005111195,"about_ca_topic_score_gemma":0.001811934,"domain_scores_codex":[0.9985322,0.0005229659,0.00007498677,0.0003196223,0.0003919774,0.0001582293],"domain_scores_gemma":[0.979122,0.01546382,0.001580325,0.001795606,0.001596045,0.0004423004],"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":[0.0002172825,0.00008604936,0.02539504,0.0001573822,0.00008930208,0.0004442531,0.001301649,0.1088614,0.001792237,0.7912844,0.005505046,0.06486596],"study_design_scores_gemma":[0.00004669122,0.00004850066,0.01342497,0.00005841326,0.00001970189,0.000434381,0.0002559889,0.3289407,0.0007138711,0.650872,0.005096481,0.00008840349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3269103,0.002324254,0.6344466,0.002465076,0.0001091196,0.0003424719,0.001327632,0.0009521432,0.03112241],"genre_scores_gemma":[0.9517121,0.0009828242,0.04231907,0.0002549535,0.0001816182,0.0003423853,0.0005562752,0.00007787613,0.003573025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005111195,"threshold_uncertainty_score":0.01697689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00520636905561305,"score_gpt":0.2558624053061282,"score_spread":0.2506560362505151,"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."}}