{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002645286,0.0001825297,0.00025159,0.0002716699,0.0002768647,0.0003267234,0.0007701624,0.00007335803,0.00000768728],"category_scores_gemma":[0.0001418928,0.0001378456,0.00006353374,0.0006496166,0.00003703552,0.0004193031,0.0001685993,0.0002648862,0.000004765541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003245561,"about_ca_system_score_gemma":0.000311246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001481635,"about_ca_topic_score_gemma":0.0004069028,"domain_scores_codex":[0.9980533,0.00009489251,0.0002935621,0.0006947683,0.0003666,0.0004968371],"domain_scores_gemma":[0.9982838,0.0002714716,0.00008500289,0.000942862,0.000216104,0.000200749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001211986,0.0003851449,0.0001592055,0.0001109136,0.000147234,0.00005534215,0.009665196,0.1370659,0.598026,0.0143693,0.0003114264,0.2395831],"study_design_scores_gemma":[0.0004270573,0.0001045539,0.00007010472,0.00002053738,0.0000278505,0.00001983588,0.0002367485,0.909895,0.0886113,0.00002692535,0.0003410529,0.0002190118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2018302,0.000008443863,0.7971098,0.0003190538,0.0001339745,0.0001133893,0.00001600651,0.0001765898,0.0002924962],"genre_scores_gemma":[0.4469687,4.89053e-7,0.5526834,0.0001026288,0.0001134824,0.000006222637,0.00001376059,0.00001092885,0.00010037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7728291,"threshold_uncertainty_score":0.5621181,"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."}}