{"id":"W2805552138","doi":"10.1007/978-3-319-92058-0_80","title":"Identifying Similar Sentences by Using N-Grams of Characters","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Syntax; Similarity (geometry); Grammar; Range (aeronautics); Categorization; Linguistics; Image (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":[0.000558821,0.001397215,0.0009005849,0.005565228,0.001152533,0.001377174,0.0006131907,0.001044411,0.007234911],"category_scores_gemma":[0.003155306,0.0003205916,0.0009557578,0.003405521,0.0003597358,0.002087492,0.0009197899,0.0007869487,0.006909212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003913107,"about_ca_system_score_gemma":0.000848417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001776419,"about_ca_topic_score_gemma":0.003966196,"domain_scores_codex":[0.9991124,0.0001383806,0.0001270579,0.0003071823,0.0002489228,0.00006601361],"domain_scores_gemma":[0.997694,0.001033084,0.000320018,0.0002146124,0.0005999971,0.0001382051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001726092,0.0005209547,0.01864998,0.001491812,0.0002681062,0.002359095,0.00124063,0.00184516,0.2684498,0.003436089,0.03102268,0.6689897],"study_design_scores_gemma":[0.0003108386,0.003056507,0.1178628,0.0009872245,0.001948191,0.01321224,0.005791487,0.3713261,0.2761976,0.03584666,0.1730192,0.0004412127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6117464,0.005052882,0.3023219,0.001314187,0.001817356,0.00164843,0.02766668,0.0177275,0.03070471],"genre_scores_gemma":[0.5615494,0.001431423,0.394167,0.0004672672,0.0007538887,0.0004868637,0.02831334,0.001081411,0.01174939],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007234911,"threshold_uncertainty_score":0.02420318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02587051241459214,"score_gpt":0.2853000987032469,"score_spread":0.2594295862886547,"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."}}