{"id":"W2098320952","doi":"10.1109/nlpke.2010.5587782","title":"An unsupervised approach to preposition error correction","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Natural language processing; Set (abstract data type); n-gram; Artificial intelligence; Error detection and correction; State (computer science); Data set; Information retrieval; Language model; Algorithm; Programming language","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001693953,0.00007782035,0.00006126164,0.00009343075,0.00008758529,0.0002191977,0.0006164797,0.00007199156,0.00001050904],"category_scores_gemma":[0.00002821935,0.00006350859,0.00001923081,0.0003112758,0.0000110566,0.0007631308,0.00007843215,0.0001732726,0.00001847716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001526316,"about_ca_system_score_gemma":0.00002199113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007998069,"about_ca_topic_score_gemma":0.00002173613,"domain_scores_codex":[0.999292,0.00002383304,0.00009345516,0.0003099591,0.0001486406,0.0001321447],"domain_scores_gemma":[0.9992973,0.00001011245,0.00002420437,0.0004872036,0.00008731688,0.00009385942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001006249,0.000263585,0.0001861283,0.00001213078,0.000003553426,0.000002698527,0.001489049,0.00002714251,0.7339454,0.07894954,0.003714175,0.1813965],"study_design_scores_gemma":[0.0001189651,0.000187595,0.0008768209,0.000009872249,0.000003676544,0.0001144395,0.00004155137,0.430033,0.5585682,0.009123832,0.0006006217,0.0003214179],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02619634,0.000008892994,0.9634222,0.0002249532,0.0004978444,0.0001693487,1.864384e-7,0.001507033,0.007973216],"genre_scores_gemma":[0.4940415,5.39421e-8,0.5053706,0.000300567,0.0000369371,0.00001612901,0.000002344206,0.000003461132,0.0002284851],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4678451,"threshold_uncertainty_score":0.2589805,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0111870665181936,"score_gpt":0.2746830486484927,"score_spread":0.2634959821302991,"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."}}