{"id":"W2077409459","doi":"10.1504/ijamc.2008.018504","title":"Keyword extraction rules based on a part-of-speech hierarchy","year":2008,"lang":"en","type":"article","venue":"International Journal of Advanced Media and Communication","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Hierarchy; Natural language processing; Artificial intelligence; Sentence; Domain (mathematical analysis); Set (abstract data type); Field (mathematics); Context (archaeology); Natural language; Keyword extraction; Natural language understanding","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":[0.0002928025,0.00009595665,0.0001822376,0.0003584958,0.00006992028,0.0000237024,0.001043222,0.00004288591,0.000008023418],"category_scores_gemma":[0.0002812422,0.00008639808,0.00008971876,0.0001616617,0.0001084725,0.0007962561,0.0001009188,0.0002407586,0.000001789517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000714618,"about_ca_system_score_gemma":0.00007068049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004566803,"about_ca_topic_score_gemma":0.000005358386,"domain_scores_codex":[0.9986748,0.0000972006,0.0004700162,0.0001170267,0.0005560066,0.00008498044],"domain_scores_gemma":[0.9976513,0.0005198756,0.0006744244,0.0004168662,0.0006747012,0.00006283326],"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":[0.000221767,0.0002925915,0.001300793,0.000005567266,0.00007422975,0.00004785547,0.0009695253,0.001959107,0.008100069,0.01715824,0.0001922431,0.969678],"study_design_scores_gemma":[0.008421412,0.002074545,0.06055212,0.002215803,0.0001314976,0.001968995,0.0005495427,0.127583,0.3276369,0.3266389,0.1408519,0.001375393],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1825396,0.001145182,0.8096654,0.004749931,0.0004503867,0.0001093359,0.000004259779,0.000064518,0.001271353],"genre_scores_gemma":[0.7238899,0.003036904,0.2728585,0.0001204382,0.00006136544,0.000004453402,0.000006938882,0.000005076394,0.00001640115],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9683026,"threshold_uncertainty_score":0.3523211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02188772436916468,"score_gpt":0.3129724551895625,"score_spread":0.2910847308203978,"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."}}