{"id":"W2052227241","doi":"10.1145/1289600.1289602","title":"Adaptive text correction with Web-crawled domain-dependent dictionaries","year":2007,"lang":"en","type":"article","venue":"ACM Transactions on Speech and Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Trigram; Vocabulary; Natural language processing; Domain (mathematical analysis); Information retrieval; Word (group theory); Artificial intelligence; Web page; Crawling; Punctuation; Linguistics; World Wide Web","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":[0.001528184,0.001217148,0.001257423,0.003146449,0.000654217,0.001217049,0.001362612,0.0008773308,0.001766398],"category_scores_gemma":[0.02153648,0.000702237,0.000598648,0.002912188,0.0005772642,0.002558507,0.00148824,0.001021871,0.002889173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004148117,"about_ca_system_score_gemma":0.001140989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004798142,"about_ca_topic_score_gemma":0.0073139,"domain_scores_codex":[0.9979928,0.0006028052,0.0002432243,0.0005223465,0.0005574821,0.00008143405],"domain_scores_gemma":[0.9814299,0.008723803,0.001101576,0.005027774,0.003455435,0.000261412],"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":[0.0007466272,0.0007396204,0.01350457,0.0009826246,0.0002695053,0.0007490371,0.001371365,0.02896707,0.09859189,0.001854209,0.01249772,0.8397259],"study_design_scores_gemma":[0.000277876,0.0006226463,0.01274206,0.0001275724,0.0003289746,0.001674297,0.0008417614,0.6800956,0.2670591,0.003618448,0.03242031,0.000191492],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2529732,0.001184369,0.6590394,0.0003326262,0.000270491,0.0008032728,0.002017205,0.07972155,0.003657857],"genre_scores_gemma":[0.3005859,0.0005381117,0.6807449,0.0001924931,0.00007964262,0.000465995,0.006483802,0.003689079,0.007220119],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004798142,"threshold_uncertainty_score":0.009540439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008003122257323006,"score_gpt":0.25074320704803,"score_spread":0.2427400847907071,"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."}}