{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003611872,0.00209719,0.001440599,0.001491431,0.0008395759,0.00229795,0.001370142,0.001601988,0.002382676],"category_scores_gemma":[0.0269766,0.0005876494,0.0009307643,0.001828822,0.0008574504,0.005993343,0.004253999,0.002664868,0.004083037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004568486,"about_ca_system_score_gemma":0.0008043894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001052837,"about_ca_topic_score_gemma":0.002367821,"domain_scores_codex":[0.9956812,0.001870815,0.0003686188,0.001171582,0.000724364,0.0001833919],"domain_scores_gemma":[0.985462,0.007660795,0.000664506,0.004142582,0.001795212,0.0002749523],"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":[0.0008959395,0.0005847532,0.01384128,0.0008379334,0.0003058354,0.0004309714,0.001613954,0.04568527,0.06224244,0.01064346,0.01787312,0.845045],"study_design_scores_gemma":[0.00009053882,0.000590908,0.005888468,0.000173156,0.0001858785,0.001312008,0.001216506,0.8349933,0.08490719,0.04929381,0.0212191,0.0001291842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1797817,0.00134737,0.8041962,0.0007539605,0.0005217202,0.0001823887,0.000962969,0.009603278,0.00265042],"genre_scores_gemma":[0.628977,0.0007517647,0.3555754,0.0005649633,0.000289551,0.0002614417,0.006022662,0.001772325,0.005784817],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003611872,"threshold_uncertainty_score":0.01910168,"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."}}