{"id":"W2752083635","doi":"10.1145/3103010.3121039","title":"High-performance Computational Framework for Phrase Relatedness","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; n-gram; Phrase; Semantic similarity; Hash function; Encoding (memory); Similarity (geometry); Artificial intelligence; Computation; Natural language processing; Language model; Information retrieval; Theoretical computer science; Algorithm; Programming language","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":[0.001736395,0.001154833,0.001331011,0.002206885,0.001250218,0.002629086,0.003790564,0.00124008,0.01102145],"category_scores_gemma":[0.01160129,0.0006639457,0.001298186,0.004358027,0.0009076431,0.007077742,0.002913401,0.001901173,0.005374286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00150637,"about_ca_system_score_gemma":0.003083976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009388079,"about_ca_topic_score_gemma":0.01225128,"domain_scores_codex":[0.998059,0.0004735325,0.0001418724,0.0004365334,0.0006853074,0.0002037718],"domain_scores_gemma":[0.9969299,0.001272295,0.0001597981,0.000895551,0.0006280782,0.0001143241],"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":[0.0005125925,0.0004083222,0.002425581,0.0004247799,0.0001764776,0.0003322569,0.0004770948,0.2443089,0.010429,0.2346755,0.04655193,0.4592776],"study_design_scores_gemma":[0.00002555205,0.00002503793,0.0001332234,0.000006476153,0.00001314007,0.00005058921,0.00003858146,0.9444264,0.001487443,0.05017101,0.003607053,0.00001545803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007918372,0.0001987867,0.9826477,0.0002510619,0.00006083722,0.0001214038,0.0005662171,0.005819629,0.002415945],"genre_scores_gemma":[0.1821231,0.0002956486,0.8091378,0.0001793261,0.0002138079,0.0006908645,0.002954385,0.0007658566,0.003639257],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01102145,"threshold_uncertainty_score":0.03687048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03408190696163151,"score_gpt":0.2906712582641496,"score_spread":0.2565893513025181,"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."}}