{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004499215,0.001332203,0.001608727,0.005481374,0.001440356,0.003228218,0.002951276,0.001959086,0.01284061],"category_scores_gemma":[0.01119513,0.0007190203,0.00121858,0.003965943,0.0005793963,0.006677646,0.003596616,0.002122588,0.008959408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061473,"about_ca_system_score_gemma":0.002365503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003919296,"about_ca_topic_score_gemma":0.006841011,"domain_scores_codex":[0.9979727,0.0004067425,0.0002769918,0.0006471569,0.0006255199,0.00007092089],"domain_scores_gemma":[0.9949484,0.002242457,0.0002924268,0.0008077347,0.001372958,0.0003358967],"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":[0.001846649,0.001166315,0.005762697,0.0009522816,0.0003385262,0.001111669,0.002764553,0.003253934,0.04968616,0.0357783,0.1421923,0.7551467],"study_design_scores_gemma":[0.000376307,0.000569651,0.005760781,0.0002848042,0.0003403144,0.001920511,0.001004982,0.5669404,0.06916377,0.08129703,0.2719562,0.0003852015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007829893,0.0003682504,0.8701853,0.0006544785,0.00008843304,0.0006707911,0.004561475,0.1122282,0.003413209],"genre_scores_gemma":[0.04383859,0.0002393711,0.9359162,0.0007117267,0.00007751569,0.0009471262,0.009777539,0.001688486,0.006803339],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01284061,"threshold_uncertainty_score":0.04295605,"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."}}