{"id":"W3177727271","doi":"10.1109/access.2021.3135807","title":"Comparative Analysis of Word Embeddings in Assessing Semantic Similarity of Complex Sentences","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Computer science; Natural language processing; Artificial intelligence; Semantic similarity; Word embedding; Sentence; Benchmark (surveying); Readability; Word (group theory); Similarity (geometry); Transformer; Embedding; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000278942,0.00009394505,0.0005323071,0.0003097547,0.00003562472,0.0001499038,0.0008627894,0.0000374835,0.00002738325],"category_scores_gemma":[0.00003452896,0.00009283698,0.0001035108,0.002412258,0.00005830516,0.0008170935,0.0002630798,0.0001035905,4.9227e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002397235,"about_ca_system_score_gemma":0.00008853053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005002938,"about_ca_topic_score_gemma":0.0008139905,"domain_scores_codex":[0.99864,0.0001256074,0.0004406948,0.000328723,0.0003007363,0.0001642369],"domain_scores_gemma":[0.9988912,0.0002116476,0.0002482959,0.0003962459,0.0002189853,0.00003366038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001008439,0.0005078161,0.6475719,0.0002453852,0.0008568333,0.00009611198,0.009558584,0.2842722,0.04344194,0.004844948,0.0001703745,0.008423808],"study_design_scores_gemma":[0.0001139663,0.000004095886,0.1766605,0.00005038601,0.00006250799,0.000001116848,0.0002791347,0.7970818,0.02483469,0.000817634,0.000007495487,0.00008665578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6756885,0.00004261678,0.3233606,0.0001459476,0.00009409136,0.00003600964,0.000001951214,0.00001275031,0.0006175099],"genre_scores_gemma":[0.9815494,0.000005709571,0.01832768,0.00008785818,0.00001091214,0.000001894596,0.000002741046,0.000001872748,0.00001192661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5128096,"threshold_uncertainty_score":0.3785782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1432759075099785,"score_gpt":0.4075290179436385,"score_spread":0.26425311043366,"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."}}