{"id":"W2133503566","doi":"10.3115/1642011.1642021","title":"An unsupervised model for text message normalization","year":2009,"lang":"en","type":"article","venue":"","topic":"Digital Communication and Language","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Normalization (sociology); Computer science; Natural language processing; Artificial intelligence; Text messaging; Text message; Phone; Set (abstract data type); Test set; Construct (python library); Word (group theory); Variety (cybernetics); World Wide Web; 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":[0.00009556243,0.00005134799,0.00004880137,0.00003703706,0.00005980059,0.0001848894,0.0007157128,0.00002150106,0.00001428967],"category_scores_gemma":[0.000008292694,0.00004413358,0.00002559808,0.000122327,0.000005764213,0.001010372,0.00003104058,0.00002048241,0.0000117865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007480398,"about_ca_system_score_gemma":0.00001830551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000244853,"about_ca_topic_score_gemma":0.000008526614,"domain_scores_codex":[0.9995955,0.00001300417,0.00009257563,0.0001220836,0.00007805761,0.0000988062],"domain_scores_gemma":[0.9992775,0.00001359399,0.00001884108,0.0005903042,0.0000470141,0.00005279257],"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":[0.000002318215,0.00008420928,0.000005762793,0.000001484831,0.000001028973,1.675831e-7,0.000576345,0.002156438,0.0006978107,0.9296315,0.0004865887,0.06635633],"study_design_scores_gemma":[0.0001680082,0.00005155495,0.0001995001,0.000001517024,7.617788e-7,6.133398e-7,0.00002061968,0.9884599,0.0006213028,0.00837186,0.002031081,0.00007323879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001183865,0.00001842683,0.851738,0.0007736787,0.000007285622,0.00009413787,0.000001127951,0.0001926268,0.1459909],"genre_scores_gemma":[0.9053796,0.000002699885,0.08938004,0.00322721,0.000004156714,0.000005233405,0.00001776704,0.00000259666,0.001980731],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9863035,"threshold_uncertainty_score":0.1799715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0249597595725148,"score_gpt":0.2858597068773903,"score_spread":0.2608999473048755,"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."}}