{"id":"W2799060650","doi":"10.18653/v1/p18-2089","title":"Addressing Noise in Multidialectal Word Embeddings","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Natural language processing; Artificial intelligence; Boosting (machine learning); Sentence; Word (group theory); Embedding; Speech recognition; Spelling; Task (project management); Noise (video); 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":[0.0001611455,0.00006688653,0.00007663463,0.00009212357,0.0000525821,0.00009944459,0.0004241752,0.00003598598,0.00005635658],"category_scores_gemma":[0.0000431986,0.00006112052,0.00002041871,0.0002353706,0.00002949878,0.0003713223,0.0002030041,0.00007677839,0.0001147289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003051253,"about_ca_system_score_gemma":0.00003283024,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000136866,"about_ca_topic_score_gemma":0.0001441206,"domain_scores_codex":[0.9992277,0.00002026769,0.0001385282,0.0002663559,0.0001245211,0.0002225997],"domain_scores_gemma":[0.9995697,0.00003218722,0.00002478719,0.0002922571,0.0000334777,0.00004758758],"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":[0.00001305046,0.0001031702,0.01077827,0.00001597402,0.000007736238,0.00005239834,0.0107465,0.0002419128,0.0273384,0.03805052,0.001398271,0.9112538],"study_design_scores_gemma":[0.0003676899,0.00002506914,0.006220365,0.00004356971,7.429515e-7,0.000008652902,0.00003386839,0.9794428,0.01085817,0.001692064,0.001125692,0.0001813208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3647778,0.00001433933,0.6152248,0.0003003012,0.0002829637,0.00005176,6.546718e-8,0.0001277533,0.01922023],"genre_scores_gemma":[0.8199002,6.145547e-7,0.1792939,0.0002623493,0.0001289901,0.000002673837,9.439431e-8,0.000003511886,0.0004076092],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9792009,"threshold_uncertainty_score":0.2492422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05947592401808097,"score_gpt":0.3114900301775979,"score_spread":0.2520141061595169,"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."}}