{"id":"W1749331913","doi":"10.1007/978-3-642-03070-3_50","title":"New Semantic Similarity Based Model for Text Clustering Using Extended Gloss Overlaps","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; WordNet; Semantic similarity; Vector space model; Ambiguity; Cluster analysis; Natural language processing; Artificial intelligence; Explicit semantic analysis; Information retrieval; Similarity (geometry); Semantic computing; Semantic Web; Semantic technology; Image (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":[0.0005706816,0.0005796045,0.0005639284,0.000862448,0.0003727506,0.0008547218,0.003722267,0.0004617583,0.000008327611],"category_scores_gemma":[0.0001133905,0.0005599824,0.0002045556,0.0005617028,0.0003278168,0.0008405647,0.0009243478,0.0005744966,0.000006911111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004544244,"about_ca_system_score_gemma":0.001074546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001679305,"about_ca_topic_score_gemma":0.00009145554,"domain_scores_codex":[0.9961767,0.00001605513,0.0005821695,0.001658889,0.0008120397,0.0007541274],"domain_scores_gemma":[0.9972001,0.0003023364,0.0003849472,0.001737917,0.000207255,0.0001674098],"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":[0.000008193701,0.00002133752,0.000005740096,0.0000381663,0.000005106349,0.000008604713,0.0001276794,0.321206,0.0003472069,0.0155548,0.00004799641,0.6626292],"study_design_scores_gemma":[0.0003141954,0.00008189821,0.00002761303,0.0001903802,0.000009064267,0.00001060697,8.92416e-8,0.7420055,0.0010466,0.2555047,0.0003335622,0.0004758128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002005976,0.0002396864,0.995566,0.001848434,0.0006785252,0.0006640796,0.000006521335,0.0005461191,0.000430634],"genre_scores_gemma":[0.08677834,0.00001427728,0.910976,0.001404013,0.0001681301,0.000007587915,0.000004629867,0.0000298699,0.0006171604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6621534,"threshold_uncertainty_score":0.9996852,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04332717124989038,"score_gpt":0.2861407243885287,"score_spread":0.2428135531386383,"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."}}