{"id":"W3089160253","doi":"","title":"Semantic Similarity Frontiers: From Concepts to Documents","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Semantic similarity; Similarity (geometry); Semantics (computer science); Natural language processing; Information retrieval; Sentence; SemEval; Artificial intelligence; Word (group theory); Semantic computing; Component (thermodynamics); Semantic Web; Linguistics","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":[0.007030482,0.001675001,0.001905911,0.01577358,0.002269715,0.01745799,0.003467682,0.00327376,0.01632308],"category_scores_gemma":[0.04153141,0.001069481,0.001853685,0.01596973,0.009744746,0.04408064,0.008495122,0.00471483,0.004286126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004879111,"about_ca_system_score_gemma":0.003480307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004052856,"about_ca_topic_score_gemma":0.001816256,"domain_scores_codex":[0.988965,0.00489536,0.0009885584,0.001958112,0.002778987,0.0004139937],"domain_scores_gemma":[0.9829217,0.0125178,0.0006683611,0.001527841,0.001751574,0.0006126796],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001283761,0.00006267778,0.0009319545,0.002040343,0.00009078026,0.0002175926,0.004306146,0.00205643,0.0008350895,0.7062044,0.02874314,0.2543831],"study_design_scores_gemma":[0.0000190685,0.00003541071,0.000801977,0.0006318014,0.00002357598,0.0003581519,0.001929103,0.006017998,0.0005252186,0.8562193,0.1334021,0.00003633168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01829769,0.1746842,0.6704322,0.03950157,0.003943226,0.0008234538,0.005100958,0.002508083,0.08470862],"genre_scores_gemma":[0.2613195,0.07543857,0.6234647,0.005949149,0.005360733,0.001702709,0.007486814,0.001346552,0.01793126],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01745799,"threshold_uncertainty_score":0.0546062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07529857966887143,"score_gpt":0.4671359010380242,"score_spread":0.3918373213691527,"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."}}