{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009140095,0.0005087569,0.000594468,0.0007848784,0.0002177724,0.0005545868,0.004450601,0.0003454139,0.00001882616],"category_scores_gemma":[0.0001001269,0.000450116,0.0001422133,0.0007366144,0.001225094,0.001130966,0.001619556,0.00066776,0.000008355559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002320071,"about_ca_system_score_gemma":0.0003409443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005448491,"about_ca_topic_score_gemma":0.00001636994,"domain_scores_codex":[0.9961841,0.00003606968,0.0006233288,0.001373759,0.001173712,0.0006090909],"domain_scores_gemma":[0.9974222,0.0002079538,0.0006717845,0.001163615,0.0004084308,0.000126006],"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":[0.00001451513,0.00007762036,0.0001602977,0.0003961454,0.00005036205,0.0001754617,0.004113047,0.0004705971,0.04720815,0.007931907,0.0001744588,0.9392275],"study_design_scores_gemma":[0.0002448062,0.0002707599,0.00001347412,0.00296149,0.00002745005,0.0001678793,0.000001116055,0.3053506,0.1799972,0.5090923,0.0004143796,0.001458515],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006835121,0.002288093,0.9949751,0.0002211059,0.001170468,0.0002579794,0.000007205148,0.0002586156,0.0001379379],"genre_scores_gemma":[0.09530167,0.00004875341,0.9035414,0.0006969487,0.0002607772,0.000002609421,0.000005250109,0.00003363709,0.0001088944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9377689,"threshold_uncertainty_score":0.9997951,"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."}}