{"id":"W2324256469","doi":"10.14195/2182-8830_4-1_3","title":"Sentence-Alignment and Application of Russian-German Multi-Target Parallel Corpora for Linguistic Analysis and Literary Studies","year":2015,"lang":"en","type":"article","venue":"Matlit Revista do Programa de Doutoramento em Materialidades da Literatura","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Université de Montréal","keywords":"Computer science; German; Natural language processing; Sentence; Rule-based machine translation; Artificial intelligence; Set (abstract data type); Linguistics; Corpus linguistics; Parsing; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002341747,0.0006668075,0.0005545378,0.004016411,0.001503932,0.001816405,0.0006997025,0.0004729536,0.0107238],"category_scores_gemma":[0.008009371,0.0005755907,0.0006111419,0.005216762,0.0004704947,0.002417897,0.001953739,0.0008197805,0.004668755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006536829,"about_ca_system_score_gemma":0.001013005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001872729,"about_ca_topic_score_gemma":0.002742238,"domain_scores_codex":[0.9970164,0.001451333,0.0003521201,0.0006651398,0.0004356059,0.0000793696],"domain_scores_gemma":[0.9964899,0.001715772,0.0002120477,0.0006394022,0.0008602494,0.00008249224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001235804,0.0006829362,0.006849896,0.003033928,0.0002670696,0.002766224,0.01494541,0.009174854,0.1021392,0.050923,0.05157894,0.7564028],"study_design_scores_gemma":[0.0004585297,0.0006141203,0.04061935,0.0005973362,0.000374835,0.003598842,0.01206606,0.1462751,0.1777421,0.04213577,0.5752111,0.0003067922],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2096446,0.001741661,0.7058993,0.00108957,0.0007674057,0.001357793,0.019583,0.02054304,0.0393736],"genre_scores_gemma":[0.2916035,0.0008148822,0.6608228,0.0000946092,0.000123376,0.001240919,0.03265936,0.003887984,0.008752567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0107238,"threshold_uncertainty_score":0.03587466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02821082619746977,"score_gpt":0.3351590564022613,"score_spread":0.3069482302047916,"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."}}