{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002504532,0.001291337,0.001654898,0.0009369476,0.0009460165,0.001455405,0.002010991,0.001008107,0.003266811],"category_scores_gemma":[0.01644401,0.0005562445,0.0005737683,0.001268871,0.001603218,0.003872986,0.002645145,0.001823723,0.00154681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001068784,"about_ca_system_score_gemma":0.001031344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002304414,"about_ca_topic_score_gemma":0.003974861,"domain_scores_codex":[0.9977201,0.0009577001,0.00009094398,0.0005413052,0.0005200721,0.000169769],"domain_scores_gemma":[0.9945698,0.003108909,0.0002991466,0.001005601,0.0008270051,0.0001894698],"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":[0.001161034,0.0003718779,0.004405352,0.0004343222,0.0001380343,0.0002620871,0.0003697078,0.3378064,0.01268212,0.19483,0.02930669,0.4182323],"study_design_scores_gemma":[0.00003379428,0.00004479209,0.0001591962,0.000008783849,0.000007643792,0.00005583618,0.00003169339,0.9256231,0.001611832,0.0706693,0.001743666,0.0000103876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01636893,0.0004124016,0.9805839,0.0003186194,0.0001113942,0.00007450787,0.0001661982,0.0009007143,0.001063388],"genre_scores_gemma":[0.5614216,0.0006031875,0.4243048,0.0006182569,0.000504443,0.0006421009,0.003142527,0.0005030489,0.008260176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003266811,"threshold_uncertainty_score":0.01324534,"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."}}