{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003143915,0.0007602815,0.001107117,0.007292349,0.0007280442,0.002237139,0.001249035,0.001198909,0.002146382],"category_scores_gemma":[0.01858926,0.0004399002,0.001262005,0.009014906,0.001043212,0.005210376,0.001547862,0.001847455,0.0009927276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007755724,"about_ca_system_score_gemma":0.001340664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009676006,"about_ca_topic_score_gemma":0.001374253,"domain_scores_codex":[0.9961682,0.001147782,0.0005029134,0.0009950007,0.001034349,0.0001518007],"domain_scores_gemma":[0.9854317,0.01062491,0.001372121,0.001265411,0.001091996,0.0002138062],"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":[0.0007549113,0.0002560019,0.01044172,0.0009164806,0.0003432002,0.0005978415,0.001365414,0.02356758,0.03932865,0.08077025,0.005908185,0.8357498],"study_design_scores_gemma":[0.00009333996,0.0003682946,0.009499821,0.0001874368,0.0001872838,0.001731949,0.000468018,0.7744402,0.02639396,0.1602969,0.02613793,0.0001948972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01818644,0.0005319254,0.9788539,0.0002365784,0.00006170516,0.000111401,0.0006093567,0.0006971603,0.0007115539],"genre_scores_gemma":[0.2629285,0.000457737,0.7318332,0.0001812234,0.0002492843,0.0006601068,0.00219372,0.0002538897,0.001242378],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007292349,"threshold_uncertainty_score":0.01662683,"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."}}