{"id":"W3201262565","doi":"10.1075/li.00058.ior","title":"Minimodel of semantic synthesis of Russian sentences","year":2021,"lang":"en","type":"article","venue":"Lingvisticae Investigationes","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Lexicalization; Lexicographical order; Computer science; Representation (politics); Natural language processing; Artificial intelligence; Matching (statistics); Linguistics; Mathematics; Philosophy","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":[0.0001778863,0.00009969765,0.0002283409,0.0001012242,0.00005010368,0.0000574179,0.0004877373,0.00005818897,0.000007456504],"category_scores_gemma":[0.001566163,0.00008950799,0.00005382287,0.0005235678,0.0002140096,0.0002370139,0.0001494001,0.00007442736,0.000002786245],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008710478,"about_ca_system_score_gemma":0.0001898279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003909219,"about_ca_topic_score_gemma":0.000003888622,"domain_scores_codex":[0.9989221,0.00006512408,0.0003699808,0.0002459258,0.0002717113,0.0001251439],"domain_scores_gemma":[0.9987003,0.0003527158,0.0002321622,0.0003983272,0.0002571999,0.00005928436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00000205461,0.00006453641,0.001894809,0.0003537579,0.00002444991,0.00001820281,0.0006165684,0.00003620279,0.0572599,0.9300398,0.00006634359,0.009623399],"study_design_scores_gemma":[0.00003464436,0.0000138716,0.0003873308,0.0003157587,0.00001852554,0.00001274364,0.0000407602,0.03152875,0.7312857,0.2362401,0.00002134523,0.0001005122],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05850789,0.001820425,0.934154,0.003757042,0.0001963242,0.0001016774,0.00001182497,0.000287502,0.001163295],"genre_scores_gemma":[0.5507751,0.000007429612,0.4491064,0.00005365613,0.0000159181,0.000004156767,0.000001648858,0.000003632086,0.00003211336],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6937997,"threshold_uncertainty_score":0.365003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01747218787358303,"score_gpt":0.2576618983789042,"score_spread":0.2401897105053211,"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."}}