{"id":"W3091895957","doi":"10.1007/978-3-030-60887-3_19","title":"Evaluation of Similarity Measures in a Benchmark for Spanish Paraphrasing Detection","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Paraphrase; Similarity (geometry); Computer science; Natural language processing; Artificial intelligence; Vocabulary; Benchmark (surveying); Semantic similarity; Boundary (topology); Computation; Information retrieval; Linguistics; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004895732,0.002312136,0.001849847,0.007838544,0.001477106,0.003183865,0.002770788,0.002837672,0.006730955],"category_scores_gemma":[0.02174027,0.0003636499,0.001075134,0.005231481,0.0006317583,0.003471755,0.002999944,0.001219907,0.005757358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001007743,"about_ca_system_score_gemma":0.001254827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006718265,"about_ca_topic_score_gemma":0.008006216,"domain_scores_codex":[0.9933775,0.002022402,0.0009971136,0.001572739,0.00164004,0.000390259],"domain_scores_gemma":[0.9827206,0.007632533,0.0007780318,0.0023513,0.005259837,0.001257663],"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":[0.005604555,0.004224599,0.01693778,0.004581843,0.001108463,0.001093511,0.00124463,0.0165299,0.06013396,0.002807314,0.05923706,0.8264963],"study_design_scores_gemma":[0.002621565,0.008548601,0.09561217,0.0006307201,0.001155696,0.004464874,0.005151675,0.6728785,0.1449472,0.007606424,0.05594873,0.0004339073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.825232,0.01093946,0.08658902,0.0006082779,0.00128383,0.001824418,0.02149947,0.02841361,0.02360984],"genre_scores_gemma":[0.7053131,0.001712097,0.1798425,0.0003114941,0.0003863945,0.000893425,0.1001168,0.001808125,0.009616056],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007838544,"threshold_uncertainty_score":0.02589142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0693253929892796,"score_gpt":0.2915309333346245,"score_spread":0.222205540345345,"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."}}