{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00126334,0.0002144853,0.0003662659,0.000171694,0.00006934028,0.0002908559,0.001042906,0.0001314226,0.00000747528],"category_scores_gemma":[0.001594405,0.0001827501,0.00005534931,0.0007823197,0.00003590989,0.0007759496,0.0005698829,0.0005199993,0.00001471375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002055264,"about_ca_system_score_gemma":0.0001371715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002315057,"about_ca_topic_score_gemma":0.00002187835,"domain_scores_codex":[0.9974476,0.0005518741,0.0003959787,0.0007059301,0.0004431284,0.0004555464],"domain_scores_gemma":[0.9988149,0.0002237542,0.00009846788,0.000483926,0.0001016344,0.0002772476],"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":[0.00001986182,0.00004386618,0.005573899,0.00002163697,0.000009660027,0.00009224698,0.0189201,0.0002143918,0.001169386,0.00005360104,0.0008722548,0.9730091],"study_design_scores_gemma":[0.00128963,0.00006346596,0.002925541,0.0002598941,0.00001770892,0.00001515681,0.002165546,0.9583789,0.007329362,0.02333709,0.003428039,0.0007897062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04856025,0.01069447,0.9368423,0.001973785,0.001045849,0.0001822592,0.000001238725,0.0001946557,0.0005051718],"genre_scores_gemma":[0.3486829,9.403016e-7,0.6490756,0.001987621,0.0001281952,0.000008671129,0.000001816768,0.000009349011,0.0001048853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9722194,"threshold_uncertainty_score":0.7452333,"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."}}