{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002676602,0.00009924403,0.0001128921,0.00006858951,0.00008981638,0.0001343238,0.0006263022,0.00005696917,0.00009337331],"category_scores_gemma":[0.00001678267,0.00009256012,0.00004820451,0.0001153622,0.00001388944,0.0004722327,0.0002793798,0.0002792228,0.0004761858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004814541,"about_ca_system_score_gemma":0.00006862387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002318096,"about_ca_topic_score_gemma":0.00004797289,"domain_scores_codex":[0.9987917,0.00004135993,0.0001829494,0.0004038011,0.0002744903,0.0003057177],"domain_scores_gemma":[0.9993589,0.0000697018,0.00002605831,0.0004138711,0.00004003933,0.00009146405],"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":[0.000001108217,0.00001289504,0.000275032,0.000001611456,0.000004397428,0.00000308974,0.001317284,0.9306456,0.0007242596,0.01275757,0.00007550007,0.05418163],"study_design_scores_gemma":[0.0001169375,0.000009126959,0.0000356505,0.000007749727,0.000001427183,0.000001816026,0.00005591405,0.9953987,0.001305766,0.002351157,0.0005946535,0.0001210745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1568459,0.00005949983,0.8313735,0.001413666,0.00005770355,0.00004833828,2.245268e-7,0.0002404638,0.00996075],"genre_scores_gemma":[0.5794252,0.000005288627,0.4164932,0.0003174623,0.0001173583,0.000001041628,6.334087e-7,0.000005749944,0.003634093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4225793,"threshold_uncertainty_score":0.6120564,"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."}}