{"id":"W2129198817","doi":"10.1109/icdmw.2009.49","title":"Parameterized Contrast in Second Order Soft Co-occurrences: A Novel Text Representation Technique in Text Mining and Knowledge Extraction","year":2009,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Contrast (vision); Representation (politics); Natural language processing; Artificial intelligence; Knowledge extraction; Meaning (existential); Parameterized complexity; Information extraction; Information retrieval; Co-occurrence; Relationship extraction; Word (group theory); Linguistics; Algorithm","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":[0.0004531226,0.0001285711,0.0001981343,0.0002694527,0.00003887948,0.0001349919,0.0002241002,0.00009762467,0.00004846458],"category_scores_gemma":[0.0001262594,0.0001248437,0.00001917697,0.0004838597,0.00002578051,0.0007489162,0.00004523858,0.0001540249,0.000003772582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004976107,"about_ca_system_score_gemma":0.0000808381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001003641,"about_ca_topic_score_gemma":0.0005341683,"domain_scores_codex":[0.9987326,0.00006874426,0.0003795326,0.0004757795,0.0001129876,0.0002303207],"domain_scores_gemma":[0.9993151,0.0002365232,0.00009012456,0.000260239,0.00004757399,0.00005046786],"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":[0.00005732299,0.0005318088,0.01458924,0.00003954827,0.000008462302,0.00002398795,0.007531103,0.0004470201,0.1575159,0.006897025,0.0002441792,0.8121144],"study_design_scores_gemma":[0.002944987,0.0001440276,0.05531617,0.0001722242,0.00000335913,0.00008356579,0.0005811938,0.9252089,0.01198527,0.002344796,0.0007647462,0.0004507736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2716374,0.00005163756,0.7240527,0.000201927,0.00006982822,0.0003234244,8.686044e-7,0.00007159427,0.003590642],"genre_scores_gemma":[0.8549011,0.000006779569,0.144752,0.0001246973,0.00001742141,0.00004208201,0.000001933309,0.000003470673,0.0001505435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9247619,"threshold_uncertainty_score":0.5090978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04513540965388924,"score_gpt":0.3360023972293884,"score_spread":0.2908669875754992,"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."}}