{"id":"W2910606374","doi":"10.1145/3265752","title":"Low-Resource Machine Transliteration Using Recurrent Neural Networks","year":2019,"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":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Transliteration; Computer science; Grapheme; Pronunciation; Artificial intelligence; Machine translation; Word error rate; Natural language processing; Speech recognition; Artificial neural network; Vietnamese; Translation (biology); Recurrent neural network; Sequence (biology); Linguistics","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":[0.0006718987,0.0008517774,0.0006655459,0.0004198608,0.0002670654,0.0005302611,0.0009454533,0.000536689,0.002094378],"category_scores_gemma":[0.002341385,0.0002857252,0.0005632946,0.0005404521,0.0002950933,0.001121542,0.0006336065,0.0009080397,0.001366883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005321517,"about_ca_system_score_gemma":0.0006851638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004412966,"about_ca_topic_score_gemma":0.007189263,"domain_scores_codex":[0.9994776,0.0001644809,0.00004400983,0.0001570999,0.0001047919,0.00005203261],"domain_scores_gemma":[0.9989725,0.0005131313,0.0001079508,0.0001613032,0.0002234156,0.00002173911],"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":[0.0003971446,0.0001780422,0.0007125206,0.0003101395,0.000162473,0.0004018327,0.0001800971,0.4202937,0.05690153,0.005611008,0.004195207,0.5106563],"study_design_scores_gemma":[0.00001176319,0.00006072993,0.0001337313,0.000007484959,0.00002502199,0.00005504137,0.00001228548,0.981508,0.01525326,0.001871301,0.001052088,0.000009321801],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03970216,0.0005108735,0.9510797,0.0001382331,0.0000845777,0.00005974155,0.0001718226,0.006079283,0.002173571],"genre_scores_gemma":[0.6053345,0.0004832689,0.3859172,0.000163976,0.00007108618,0.000210572,0.001312622,0.0004806114,0.006026217],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004412966,"threshold_uncertainty_score":0.008774579,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006320644909480506,"score_gpt":0.2400011345345139,"score_spread":0.2336804896250334,"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."}}