{"id":"W2946532448","doi":"10.1145/3292500.3330727","title":"A User-Centered Concept Mining System for Query and Document Understanding at Tencent","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Knowledge base; Web query classification; Web search query; Web mining; Taxonomy (biology); Query language; Core (optical fiber); Database query","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":[0.0001840585,0.0001305807,0.0002188983,0.00008753243,0.0001091606,0.0001311899,0.0003347639,0.00004072606,0.00001186744],"category_scores_gemma":[0.000008596809,0.0001083959,0.00006572463,0.0001405717,0.00002921181,0.0004850678,0.0003442404,0.00003463947,0.000007822846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006098953,"about_ca_system_score_gemma":0.00001752901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001248302,"about_ca_topic_score_gemma":0.00001779991,"domain_scores_codex":[0.998873,0.00002613977,0.0002287377,0.0004288203,0.0001831392,0.0002601853],"domain_scores_gemma":[0.9992483,0.0001325708,0.0001147029,0.0003923591,0.00003807004,0.00007401063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002542812,0.00002393679,0.007739138,0.0001513426,0.00009613319,0.000007852138,0.001443898,0.00009329066,0.005739697,0.9774673,0.001579781,0.005632184],"study_design_scores_gemma":[0.01159384,0.002383534,0.001800817,0.00265979,0.0002569984,0.0002720156,0.03090959,0.5765752,0.2803217,0.05340302,0.03548216,0.004341365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02472922,0.00009043643,0.972693,0.0002290509,0.0001289989,0.000452399,0.000001154915,0.0003717206,0.001303972],"genre_scores_gemma":[0.8177587,0.000007533173,0.1810308,0.0001028581,0.00001209577,0.00002628566,0.000001675102,0.000007565158,0.001052497],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9240643,"threshold_uncertainty_score":0.4420255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02961210578107067,"score_gpt":0.2768240722171036,"score_spread":0.2472119664360329,"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."}}