{"id":"W2170962714","doi":"10.3115/1611528.1611532","title":"Active learning for the identification of nonliteral language","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Literal (mathematical logic); Cluster analysis; Context (archaeology); Identification (biology); Artificial intelligence; Natural language processing; Selection (genetic algorithm); Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006311602,0.00003370427,0.0000406192,0.00003115388,0.00008174087,0.00003485181,0.0002624777,0.00001375056,0.000006855281],"category_scores_gemma":[0.0001064281,0.00002118284,0.00002929903,0.0001313241,0.00001291098,0.0000982574,0.00003745542,0.00007461732,0.000005072547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005551043,"about_ca_system_score_gemma":0.000007695544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005348706,"about_ca_topic_score_gemma":0.000004873438,"domain_scores_codex":[0.9995883,0.0000171212,0.0001214574,0.00009591037,0.00008558438,0.00009163796],"domain_scores_gemma":[0.999428,0.0002841253,0.00007906301,0.000148669,0.00004664548,0.0000135431],"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":[0.000006640414,0.0000169449,0.0003263062,0.00000704044,0.00001045935,5.661012e-7,0.00475553,0.0006622829,0.009448192,0.01709747,0.00006686797,0.9676017],"study_design_scores_gemma":[0.0002501278,0.00006845574,0.02574377,0.000005703563,0.00000524728,0.00000410153,0.0008496742,0.8924741,0.07398499,0.000374741,0.006153326,0.0000857802],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02955986,0.00003228538,0.9685751,0.0003429041,0.0001134786,0.0000744997,3.680265e-7,0.00005055952,0.001250955],"genre_scores_gemma":[0.9807363,8.761028e-7,0.01504847,0.00005428157,0.00006460874,0.000003148277,0.000001838689,0.000002466365,0.004088014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9675159,"threshold_uncertainty_score":0.08638111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007260639940655844,"score_gpt":0.2925523322964307,"score_spread":0.2852916923557748,"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."}}