{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001638746,0.001734823,0.0008199036,0.001717013,0.0005439724,0.001216204,0.001617743,0.001274565,0.003307508],"category_scores_gemma":[0.007706287,0.0004138675,0.00104341,0.002071849,0.0007222221,0.003688307,0.001311238,0.003057599,0.005081843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118579,"about_ca_system_score_gemma":0.001438543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00593925,"about_ca_topic_score_gemma":0.01009379,"domain_scores_codex":[0.9985291,0.000415438,0.0001212687,0.000554646,0.0002787002,0.0001009167],"domain_scores_gemma":[0.9973132,0.0009581562,0.0002999932,0.0006372685,0.0007077355,0.00008364319],"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":[0.0003860384,0.0003847776,0.002408602,0.0003133038,0.0001185965,0.0003049047,0.0002265831,0.1378146,0.03126303,0.00894955,0.02802657,0.7898034],"study_design_scores_gemma":[0.00001936667,0.0001015092,0.0005376591,0.00002322954,0.00002768201,0.0001327898,0.00005888573,0.9529775,0.01970188,0.01649912,0.009891768,0.00002869035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03381171,0.0009443308,0.9413759,0.0007078433,0.0005468128,0.000233786,0.0017405,0.01797465,0.002664437],"genre_scores_gemma":[0.346954,0.001054707,0.6151814,0.0007316839,0.000390896,0.0006202111,0.01526528,0.001778747,0.01802303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00593925,"threshold_uncertainty_score":0.01180935,"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."}}