{"id":"W2160039544","doi":"10.3115/1220575.1220695","title":"Learning a spelling error model from search query logs","year":2005,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spelling; Edit distance; String (physics); Artificial intelligence; Language model; Measure (data warehouse); Natural language processing; Maximization; Data mining; Mathematics; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005051795,0.001377594,0.001926618,0.00185654,0.000507173,0.001869386,0.002150899,0.001821813,0.001005833],"category_scores_gemma":[0.0286506,0.0007933756,0.0009651681,0.002059401,0.0009148058,0.004835849,0.001109637,0.00279222,0.001026367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001366786,"about_ca_system_score_gemma":0.001997396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009312312,"about_ca_topic_score_gemma":0.00842378,"domain_scores_codex":[0.9976256,0.0007857805,0.0001873837,0.0007823469,0.0004115435,0.0002073436],"domain_scores_gemma":[0.9815089,0.01374363,0.00128682,0.001483583,0.001719249,0.0002577747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001093958,0.0006451895,0.02092167,0.0004502701,0.0002880682,0.0003011378,0.000518323,0.6951998,0.01451768,0.009166723,0.005508343,0.2513888],"study_design_scores_gemma":[0.00001737088,0.00005108011,0.0007673771,0.000006381797,0.00001928301,0.00004322666,0.00001882339,0.9934043,0.001921098,0.0035194,0.0002152038,0.00001642804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1687856,0.0005225415,0.8247105,0.0008922307,0.00008921463,0.0001239331,0.0009998505,0.002992723,0.0008833623],"genre_scores_gemma":[0.8873196,0.0004365128,0.1053136,0.0002096845,0.000199138,0.0002191776,0.002560911,0.000339454,0.003401946],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009312312,"threshold_uncertainty_score":0.02671677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06240637277141359,"score_gpt":0.286511316728582,"score_spread":0.2241049439571685,"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."}}