{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002499174,0.001697218,0.001317094,0.00605567,0.001629203,0.001660828,0.002730107,0.00144815,0.003618784],"category_scores_gemma":[0.01441504,0.000631263,0.001276817,0.004219225,0.001158198,0.002554205,0.001901703,0.002455363,0.005611551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006066588,"about_ca_system_score_gemma":0.003379761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003706207,"about_ca_topic_score_gemma":0.008757082,"domain_scores_codex":[0.993771,0.001513639,0.0004957604,0.001792008,0.002183527,0.0002439944],"domain_scores_gemma":[0.9814011,0.006173192,0.001977236,0.00355642,0.006662852,0.0002291536],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003508645,0.0002919913,0.007774299,0.0005675249,0.000299638,0.0004671203,0.0004558932,0.01073018,0.06213335,0.005545411,0.01822718,0.8931565],"study_design_scores_gemma":[0.00008126954,0.0003222953,0.01903482,0.0001604117,0.0002484264,0.003161579,0.0007746527,0.6607698,0.2214086,0.02746148,0.06617481,0.0004018883],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02443686,0.0003778758,0.954735,0.0002397261,0.0002952357,0.0002875764,0.001529277,0.0148283,0.003270213],"genre_scores_gemma":[0.1455635,0.0002779327,0.8405151,0.0002659263,0.000290848,0.0003443742,0.004923977,0.001857022,0.005961209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00605567,"threshold_uncertainty_score":0.01321709,"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."}}