{"id":"W2028903960","doi":"10.1109/wi-iat.2010.267","title":"An Efficient Method for Tagging a Query with Category Labels Using Wikipedia towards Enhancing Search Engine Results","year":2010,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Web query classification; Information retrieval; Web search query; Search engine; Query expansion; Set (abstract data type); Sargable; Matching (statistics); Noise (video); Query optimization; Data mining; Artificial intelligence; 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":[0.001908438,0.0008029091,0.000782662,0.004345162,0.0009530286,0.001464299,0.001145551,0.0009530944,0.001386595],"category_scores_gemma":[0.009256173,0.0004791509,0.0006222213,0.00287033,0.0008481591,0.002555216,0.001816605,0.0009041792,0.001710127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007207899,"about_ca_system_score_gemma":0.001631582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004525391,"about_ca_topic_score_gemma":0.007200466,"domain_scores_codex":[0.9975075,0.0006517682,0.0001824843,0.0004819315,0.001027853,0.000148454],"domain_scores_gemma":[0.9949822,0.001633493,0.0003586842,0.0009667172,0.001908978,0.0001500422],"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":[0.0004520942,0.0003185464,0.005604773,0.0004670544,0.0001085506,0.0002291542,0.0008993009,0.01223656,0.09383305,0.01843782,0.01140036,0.8560127],"study_design_scores_gemma":[0.0001391894,0.0004126232,0.006941753,0.0001323381,0.0002436426,0.001572012,0.0007425348,0.7253718,0.1677695,0.04451666,0.05173222,0.0004257135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01597274,0.0002511821,0.9782717,0.0001478623,0.00005005646,0.0001777157,0.0003853343,0.003351193,0.001392318],"genre_scores_gemma":[0.09663831,0.0001427941,0.89968,0.00008120832,0.00004707747,0.0002535789,0.0008306918,0.0003135034,0.002012882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004525391,"threshold_uncertainty_score":0.01009291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02616368340438582,"score_gpt":0.3282841899412179,"score_spread":0.3021205065368321,"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."}}