{"id":"W342307487","doi":"10.1007/978-3-319-13332-4_21","title":"A Comparison of Graph-Based and Statistical Metrics for Learning Domain Keywords","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Military College of Canada","funders":"","keywords":"Computer science; Pointwise mutual information; Graph; Pointwise; Artificial intelligence; Phrase; Machine learning; Data mining; Mutual information; Theoretical computer science; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001349198,0.0004211832,0.0009392519,0.001598697,0.0002090562,0.0002119,0.001762739,0.0002612755,0.000003868874],"category_scores_gemma":[0.0004382941,0.0003917255,0.0001381102,0.0009503125,0.000991425,0.0001920216,0.0006174544,0.0006411768,0.000001212734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001239828,"about_ca_system_score_gemma":0.000217332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008269635,"about_ca_topic_score_gemma":0.00002946699,"domain_scores_codex":[0.9966995,0.00006196486,0.0006880919,0.001219854,0.0008462685,0.000484324],"domain_scores_gemma":[0.9956162,0.0025127,0.0005539964,0.0008258763,0.0003450609,0.0001461876],"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":[0.00001182366,0.00003443021,0.0007588132,0.0001167203,0.00001659647,0.00000625931,0.0002648062,0.03085777,0.0001929971,0.1775495,0.00001840231,0.7901719],"study_design_scores_gemma":[0.0002176355,0.0004319885,0.00005796978,0.0001433612,0.00001616814,0.000003552801,1.602611e-7,0.6706572,0.001972927,0.3248673,0.001278352,0.0003534135],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005239868,0.0003445488,0.9984719,0.0001607172,0.0001822147,0.0003804808,0.000006253546,0.0001545082,0.0002469393],"genre_scores_gemma":[0.2364028,0.000009310094,0.7632995,0.0001667946,0.00005709383,0.000011106,0.000006651388,0.0000209256,0.00002585025],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7898184,"threshold_uncertainty_score":0.9998535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02113270971151466,"score_gpt":0.3197664553226307,"score_spread":0.2986337456111161,"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."}}