{"id":"W2963780471","doi":"10.18653/v1/p16-1141","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","year":2016,"lang":"en","type":"article","venue":"","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":860,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Semantic change; Word (group theory); Computer science; Natural language processing; Artificial intelligence; Linguistics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.002179067,0.0004186037,0.0003171276,0.003252746,0.000502318,0.002357918,0.0004087651,0.0007545059,0.00169076],"category_scores_gemma":[0.01934111,0.0003171089,0.0003770043,0.003323049,0.001739385,0.005542117,0.0013509,0.001302207,0.0005499463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006567592,"about_ca_system_score_gemma":0.0003324803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001377733,"about_ca_topic_score_gemma":0.002532066,"domain_scores_codex":[0.9988219,0.0003936032,0.0001413765,0.0003713967,0.000209072,0.000062632],"domain_scores_gemma":[0.9895678,0.005908888,0.001569359,0.001554169,0.0011854,0.0002143167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000676496,0.0002783228,0.2242546,0.0008158719,0.0006304663,0.0004553557,0.005830999,0.05973382,0.03419784,0.1876575,0.007787513,0.4776811],"study_design_scores_gemma":[0.00004460366,0.0002821592,0.192622,0.0001469759,0.0001811663,0.0008298274,0.002714064,0.3544225,0.0124868,0.4184449,0.01764007,0.0001849515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7115093,0.001326836,0.2743462,0.001065742,0.0002004005,0.00005634295,0.002348439,0.0005195323,0.00862708],"genre_scores_gemma":[0.9700297,0.0002896744,0.02746876,0.00008578737,0.0000533661,0.00004425281,0.001166515,0.00009846983,0.0007635088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003252746,"threshold_uncertainty_score":0.01152414,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03229225693300907,"score_gpt":0.3263275468505195,"score_spread":0.2940352899175104,"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."}}