{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001495778,0.0001234113,0.0003259883,0.002539062,0.0006672547,0.001237294,0.0004276459,0.0003140009,0.001184943],"category_scores_gemma":[0.01457359,0.0001382511,0.0003386085,0.002149511,0.001756069,0.00263143,0.0009657664,0.0005219379,0.0001415135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005645843,"about_ca_system_score_gemma":0.000323546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00241442,"about_ca_topic_score_gemma":0.003082783,"domain_scores_codex":[0.9994391,0.0002475733,0.00003959125,0.0001354201,0.00008696742,0.00005139286],"domain_scores_gemma":[0.9889205,0.007927242,0.001209522,0.0007097108,0.0008669918,0.0003660634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005537909,0.0002641637,0.5156471,0.0003220379,0.0002977132,0.0008914847,0.01231943,0.03582325,0.01882029,0.2722706,0.002619918,0.1401702],"study_design_scores_gemma":[0.0000346813,0.0001390546,0.270115,0.00006363975,0.000102141,0.0009242278,0.01042331,0.2824888,0.005609993,0.4235617,0.006435327,0.0001022815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9791947,0.0001409747,0.01897182,0.0001939097,0.000005837941,0.00000792593,0.0001745871,0.00002651136,0.001283741],"genre_scores_gemma":[0.9962166,0.00004588969,0.003404101,0.000007572756,0.00000657935,0.000009608871,0.0001538452,0.00001155545,0.0001442923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002539062,"threshold_uncertainty_score":0.00791055,"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."}}