{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003984357,0.0002576426,0.0001975287,0.0003369223,0.0006079961,0.0003317864,0.0004739928,0.0001281899,0.00002542252],"category_scores_gemma":[0.00003265876,0.0002031653,0.00004284939,0.0006823508,0.0001259396,0.0009517416,0.00002584086,0.0004818879,0.000007895179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047468,"about_ca_system_score_gemma":0.0001187917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008871258,"about_ca_topic_score_gemma":0.0004279452,"domain_scores_codex":[0.9983808,0.00003648654,0.0002382157,0.0005334304,0.0004264381,0.0003846568],"domain_scores_gemma":[0.9990073,0.0001405535,0.0001294043,0.0004357365,0.0001514523,0.0001355947],"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":[0.0001694376,0.0001009761,0.00005989874,0.00003005493,0.00002296609,0.0001331216,0.003438052,0.00001246904,0.004218705,0.0002229158,0.0000232137,0.9915682],"study_design_scores_gemma":[0.006093967,0.003307704,0.001577905,0.002102756,0.0002734762,0.00634604,0.03136396,0.03154594,0.8855633,0.02550241,0.002579642,0.003742931],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01491248,0.003459594,0.9790333,0.0004055281,0.0001916869,0.0002120649,0.000003537228,0.0009709857,0.0008108602],"genre_scores_gemma":[0.6213723,0.0000176,0.3778647,0.0002132301,0.00004592296,0.00001435225,0.000001831827,0.00001669287,0.0004533782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9878253,"threshold_uncertainty_score":0.8284841,"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."}}