{"id":"W2604963202","doi":"10.1609/aaai.v31i1.10931","title":"Distributed Negative Sampling for Word Embeddings","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Word2vec; Word (group theory); Vocabulary; Computer science; Sampling (signal processing); Artificial intelligence; Core (optical fiber); Scale (ratio); Natural language processing; Theoretical computer science; Mathematics; Linguistics; Telecommunications; Geography; Cartography","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":[0.0005512952,0.0002203704,0.0002804156,0.00007052679,0.0008290961,0.0008606206,0.004079147,0.00009290435,0.00001466788],"category_scores_gemma":[0.002081127,0.0001716198,0.0001564904,0.0001696447,0.0002817933,0.0007420554,0.0007247837,0.0002432248,0.0000203324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005371837,"about_ca_system_score_gemma":0.00008666873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005604221,"about_ca_topic_score_gemma":0.00001125383,"domain_scores_codex":[0.9981477,0.000007079156,0.0004905668,0.000580754,0.0003676603,0.0004062515],"domain_scores_gemma":[0.9975216,0.0001729574,0.0007152311,0.0006511871,0.0008471799,0.0000918759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004094635,0.00004550161,0.0001535905,0.00003046509,0.00001373995,1.238482e-7,0.000854276,0.0001288117,0.009086064,0.8988455,0.00007020081,0.09073081],"study_design_scores_gemma":[0.00004032075,0.00007515922,0.0003141558,0.0002232547,0.00001032486,0.000001511968,0.0002918864,0.2615367,0.2651952,0.4719357,0.0001672223,0.0002085692],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09162664,0.000007805562,0.8956637,0.007124551,0.0007617421,0.0006892722,0.0000214106,0.0001104349,0.003994473],"genre_scores_gemma":[0.9650316,0.000008383333,0.03452105,0.0001141587,0.0001117363,0.00005342911,5.157235e-7,0.00001158488,0.0001475318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.873405,"threshold_uncertainty_score":0.8298985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1676967713113099,"score_gpt":0.35517976344463,"score_spread":0.18748299213332,"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."}}