{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001578702,0.0007348246,0.0009860562,0.002864417,0.0007003997,0.001382246,0.001586883,0.0008666228,0.002601492],"category_scores_gemma":[0.008465464,0.0004750295,0.001044103,0.001445648,0.001123722,0.002587793,0.0006962831,0.001140152,0.002485815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005955186,"about_ca_system_score_gemma":0.001490428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002430418,"about_ca_topic_score_gemma":0.003037305,"domain_scores_codex":[0.9980667,0.0003303908,0.0002376355,0.0005703054,0.0007012802,0.00009372838],"domain_scores_gemma":[0.9953511,0.00298692,0.0002398049,0.0003183543,0.001007208,0.00009661449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000435098,0.0002316006,0.006438394,0.001372339,0.0002063215,0.001076791,0.001574968,0.0491355,0.09652194,0.02998577,0.00685038,0.806171],"study_design_scores_gemma":[0.00009433816,0.0003084667,0.0045476,0.0003208117,0.0003577867,0.001192488,0.0004698371,0.7796551,0.1014257,0.08778316,0.02371738,0.0001273831],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0171827,0.0003973204,0.9770644,0.0001837442,0.00005833538,0.0002965144,0.0005866194,0.002080339,0.002150092],"genre_scores_gemma":[0.1671251,0.0004504526,0.8280895,0.0001773043,0.00006631409,0.0003485092,0.001484473,0.0002047583,0.002053556],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002864417,"threshold_uncertainty_score":0.008702874,"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."}}