{"id":"W3001922427","doi":"10.48550/arxiv.2001.07740","title":"Where New Words Are Born: Distributional Semantic Analysis of Neologisms and Their Semantic Neighborhoods","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Neologism; Computer science; Semantic change; Semantics (computer science); Linguistics; Natural language processing; Artificial intelligence; Distributional semantics; Semantic analysis (machine learning); Phenomenon; Semantic similarity","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":[0.0001781747,0.0002343272,0.0005283486,0.0001414739,0.0002621771,0.00005599667,0.0004585271,0.0003408649,0.0004234915],"category_scores_gemma":[0.0001155938,0.0002113125,0.0003577024,0.001405289,0.0003547562,0.0001669824,0.0004363125,0.0003366169,0.00001015717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001662357,"about_ca_system_score_gemma":0.0002722772,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006985308,"about_ca_topic_score_gemma":0.009509131,"domain_scores_codex":[0.9985661,0.00022315,0.0001940542,0.0006132224,0.0001239343,0.0002795395],"domain_scores_gemma":[0.9988816,0.00009400121,0.0003472102,0.00029447,0.0001464066,0.0002363042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000288603,0.0003095254,0.623982,0.0005834813,0.007280551,0.0004662392,0.03485849,0.04164202,0.0004084163,0.2817472,0.004988682,0.003444837],"study_design_scores_gemma":[0.00169777,0.0001939504,0.663201,0.0007554021,0.01075918,0.000003625339,0.07926266,0.1317368,0.0001261992,0.105891,0.004081358,0.002291104],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9573761,0.001270442,0.03669269,0.001759242,0.0002077783,0.000277605,0.0002249219,0.000125543,0.00206569],"genre_scores_gemma":[0.9972613,0.001119289,0.00003205635,0.00006080325,0.0001611632,3.60221e-7,0.0001588133,0.000007211637,0.001199006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1758563,"threshold_uncertainty_score":0.9996272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05653445232319772,"score_gpt":0.2183685015565531,"score_spread":0.1618340492333554,"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."}}