{"id":"W2890328620","doi":"10.18653/v1/d18-1097","title":"Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Natural language processing; Normalization (sociology); Artificial intelligence; Word (group theory); Artificial neural network; Language model; Character (mathematics); Recurrent neural network; Task (project management); Sequence (biology); Arabic; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002068577,0.0001407899,0.0001218312,0.0001221824,0.0001686217,0.0003083565,0.0004975823,0.00005848257,0.000006825137],"category_scores_gemma":[0.0000354361,0.0001029036,0.00001534122,0.000310899,0.00008230042,0.001780877,0.0001786675,0.000068047,0.000005805397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003765976,"about_ca_system_score_gemma":0.00004748827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003915668,"about_ca_topic_score_gemma":0.00002605938,"domain_scores_codex":[0.9989655,0.00001239202,0.0001456631,0.0004268415,0.0001743978,0.000275218],"domain_scores_gemma":[0.9992109,0.00003651651,0.00007274042,0.0002906173,0.0002987371,0.00009047836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009372957,0.00003738768,0.0003805124,0.000126009,0.00002018324,0.00001302521,0.007866963,0.00002265912,0.08987153,0.596078,0.0008727844,0.3046172],"study_design_scores_gemma":[0.0003752898,0.0005135985,0.00008434498,0.0003224849,0.0000116613,0.0001155706,0.00007013958,0.7049004,0.1973909,0.09389354,0.00166359,0.0006585324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01858611,0.00006215707,0.9788715,0.0007523459,0.00004681455,0.0003262025,0.000002162002,0.0005509016,0.0008017606],"genre_scores_gemma":[0.4936596,0.000002875326,0.5050118,0.001029615,0.00003778173,0.00002797804,0.000001639429,0.000007708973,0.0002210515],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7048777,"threshold_uncertainty_score":0.4196288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04395995584543014,"score_gpt":0.3089185288247624,"score_spread":0.2649585729793322,"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."}}