{"id":"W4317504322","doi":"10.1145/3580495","title":"Filtering and Extended Vocabulary based Translation for Low-resource Language Pair of Sanskrit-Hindi","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sanskrit; Computer science; Machine translation; Hindi; Natural language processing; Artificial intelligence; Vocabulary; Transformer; Sentence; Phrase; Language translation; Linguistics; Engineering","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":[0.0005080866,0.0002791135,0.0002821195,0.0006934553,0.0004034665,0.0003578201,0.0005200648,0.0001824264,0.00001316638],"category_scores_gemma":[0.00009759755,0.0002660742,0.00009702698,0.0008114404,0.00009667489,0.001710801,0.00002857333,0.0002890959,0.000004088101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003467571,"about_ca_system_score_gemma":0.00006652898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001435216,"about_ca_topic_score_gemma":0.000007853946,"domain_scores_codex":[0.9983471,0.00006148129,0.0005321371,0.0003283223,0.0003647283,0.0003662572],"domain_scores_gemma":[0.998848,0.0002036574,0.0002691637,0.0004721925,0.00008123204,0.0001257655],"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":[0.0000646422,0.00003897188,0.000004935459,0.001034361,0.0000144186,0.000006404345,0.02489724,0.0002738682,0.005937858,0.00004567064,0.00004760478,0.967634],"study_design_scores_gemma":[0.003757593,0.0004744074,0.0003788582,0.002339241,0.0001054261,0.00009685861,0.01951906,0.6920033,0.2749853,0.001107698,0.003944677,0.00128764],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03574217,0.0009718077,0.9598419,0.001440305,0.00003912255,0.0005568746,0.00006431842,0.001107341,0.0002361292],"genre_scores_gemma":[0.8253198,0.00001021451,0.1736526,0.0006917038,0.00003136765,0.00007772346,0.0001172078,0.00002817878,0.00007125124],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9663464,"threshold_uncertainty_score":0.9999791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00992098405943372,"score_gpt":0.2561712473687812,"score_spread":0.2462502633093475,"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."}}