{"id":"W2118013824","doi":"10.1007/s10115-010-0367-z","title":"Statistical semantics for enhancing document clustering","year":2010,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Semantic similarity; Computer science; Cluster analysis; Document clustering; Similarity (geometry); Vector space model; Explicit semantic analysis; Semantics (computer science); Representation (politics); Benchmark (surveying); Context (archaeology); Artificial intelligence; Information retrieval; Distributional semantics; Data mining; Natural language processing; Semantic computing; Semantic technology; Semantic Web","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":[0.002960821,0.0006463801,0.001161857,0.004362243,0.0008966718,0.002245253,0.001252349,0.001040608,0.001609927],"category_scores_gemma":[0.01577654,0.0004870039,0.001138414,0.005239945,0.001095302,0.005560641,0.001895596,0.001319833,0.0008123124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000973848,"about_ca_system_score_gemma":0.00143989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001326323,"about_ca_topic_score_gemma":0.002523746,"domain_scores_codex":[0.997378,0.0008933295,0.0002572096,0.000406694,0.0009632908,0.0001015251],"domain_scores_gemma":[0.9923922,0.00365748,0.0005811307,0.001400499,0.001771549,0.0001970906],"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":[0.0005998366,0.0003936489,0.00399971,0.000673744,0.0002233608,0.000157171,0.0005300961,0.07697785,0.02591924,0.2264632,0.006540974,0.6575211],"study_design_scores_gemma":[0.00007092633,0.0001998829,0.00166419,0.00007945563,0.0001587853,0.0003144453,0.0001980679,0.6094691,0.01632606,0.3584957,0.01295867,0.00006491266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01615167,0.0005797925,0.980714,0.0002327464,0.0000763006,0.0000451606,0.0002453669,0.0009297875,0.001025146],"genre_scores_gemma":[0.3014457,0.0009334723,0.6934118,0.0002364247,0.0002657629,0.0001867938,0.001332327,0.0003702497,0.001817442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004362243,"threshold_uncertainty_score":0.0156585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01213181996842227,"score_gpt":0.3032534578081119,"score_spread":0.2911216378396896,"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."}}