{"id":"W2188556664","doi":"10.1109/wimob.2015.7347988","title":"Microtext normalization using probably-phonetically-similar word discovery","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Spelling; Normalization (sociology); Computer science; Natural language processing; Rendering (computer graphics); Artificial intelligence; Speech recognition; Word (group theory); Pattern matching; Linguistics","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":[0.001613553,0.001182808,0.001860088,0.004907236,0.001430744,0.002550376,0.002343043,0.001168923,0.006593672],"category_scores_gemma":[0.009873318,0.0006267835,0.001515315,0.004115351,0.001129696,0.005463413,0.002858182,0.001849973,0.005760282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000822705,"about_ca_system_score_gemma":0.001909379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003001017,"about_ca_topic_score_gemma":0.005123187,"domain_scores_codex":[0.9968445,0.0003692152,0.0003754985,0.001316069,0.0008912311,0.000203439],"domain_scores_gemma":[0.9940002,0.002138077,0.0007255021,0.001543742,0.001413479,0.0001789813],"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":[0.0004884188,0.0002102499,0.006489254,0.0002848376,0.0001245452,0.0003847998,0.0005052738,0.008527746,0.0464886,0.007937069,0.008591734,0.9199675],"study_design_scores_gemma":[0.0001235195,0.0002888227,0.009959786,0.0000828207,0.0002918189,0.00269582,0.001122326,0.6600242,0.2028572,0.07570058,0.04661928,0.0002339049],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04567664,0.0004491762,0.9295561,0.0003967204,0.0002573152,0.0002263264,0.001083226,0.01922741,0.003127133],"genre_scores_gemma":[0.2687243,0.0004165868,0.7154579,0.0002862654,0.0002888996,0.0002452615,0.004248458,0.001682658,0.008649793],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006593672,"threshold_uncertainty_score":0.02205801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03083235292961977,"score_gpt":0.2786322494743038,"score_spread":0.247799896544684,"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."}}