{"id":"W2949223751","doi":"10.48550/arxiv.1702.03470","title":"Vector Embedding of Wikipedia Concepts and Entities","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Embedding; Word embedding; Natural language processing; Similarity (geometry); Popularity; Artificial intelligence; Analogy; Word (group theory); Task (project management); Deep learning; Information retrieval; Linguistics; Image (mathematics)","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":[0.0005433146,0.0009279466,0.000490725,0.002553425,0.0002316654,0.0008419485,0.0006632724,0.0006226592,0.002016742],"category_scores_gemma":[0.00304485,0.0002375445,0.0006485271,0.002335275,0.0003041478,0.002352102,0.0008120436,0.0007809816,0.0009506381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004574182,"about_ca_system_score_gemma":0.0005145062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003440775,"about_ca_topic_score_gemma":0.005048891,"domain_scores_codex":[0.9994389,0.0001520597,0.00004572719,0.0001988602,0.0001185631,0.00004582629],"domain_scores_gemma":[0.9990927,0.0003172573,0.0001166755,0.0001769633,0.0002555731,0.00004074991],"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":[0.0004106526,0.0003832456,0.00755595,0.00113767,0.0003833558,0.0003506714,0.0004677302,0.1082873,0.02497997,0.02963731,0.03182507,0.794581],"study_design_scores_gemma":[0.00002779409,0.0001497577,0.004265823,0.00007980622,0.00008318732,0.0002857063,0.0001861547,0.9354877,0.01397823,0.02503841,0.02036936,0.00004797728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1584564,0.003725793,0.817985,0.0005801222,0.0005697546,0.0002635224,0.006661056,0.003821274,0.007936956],"genre_scores_gemma":[0.6827926,0.00178721,0.2897075,0.0001598405,0.0002061306,0.0002731825,0.01719004,0.0002040743,0.007679588],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003440775,"threshold_uncertainty_score":0.006841481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08734957569459353,"score_gpt":0.2230107496963628,"score_spread":0.1356611740017692,"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."}}