{"id":"W2095980495","doi":"10.1145/2740908.2742474","title":"Short-Text Clustering using Statistical Semantics","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Computer science; Term (time); Similarity (geometry); Semantics (computer science); Representation (politics); Selection (genetic algorithm); Measure (data warehouse); Computation; Space (punctuation); Data mining; Artificial intelligence; Matrix (chemical analysis); Document clustering; Pattern recognition (psychology); 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":[0.0008108693,0.0008497455,0.0009781558,0.004775308,0.000690201,0.001258011,0.001097314,0.0008971512,0.001624534],"category_scores_gemma":[0.004036254,0.0003353284,0.001173334,0.003547653,0.0006780648,0.002439787,0.000976515,0.0006541029,0.001377687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007758929,"about_ca_system_score_gemma":0.001156477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003029445,"about_ca_topic_score_gemma":0.004319252,"domain_scores_codex":[0.9990458,0.0002266548,0.00009351625,0.0002050159,0.0003775257,0.00005144869],"domain_scores_gemma":[0.9984695,0.000512734,0.0002460139,0.0002296548,0.0004881622,0.00005384294],"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":[0.0003523116,0.0001779462,0.002928398,0.0005433399,0.0002937493,0.000289639,0.0004079729,0.2746493,0.05800036,0.06013683,0.004782367,0.5974378],"study_design_scores_gemma":[0.00001994226,0.00007739889,0.001087886,0.00002691436,0.00003484399,0.0001831093,0.00008600284,0.9514675,0.008807207,0.03386905,0.004307625,0.00003264505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01102704,0.0002963153,0.9872409,0.00006363955,0.0000292376,0.00005791674,0.0001054703,0.0006648969,0.0005147177],"genre_scores_gemma":[0.1899382,0.0007220986,0.8042816,0.00009787614,0.0001548852,0.0002696729,0.0015713,0.0002390022,0.002725287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004775308,"threshold_uncertainty_score":0.006023586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1306881645226687,"score_gpt":0.3815659194037594,"score_spread":0.2508777548810908,"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."}}