{"id":"W3165821503","doi":"10.18653/v1/2021.calcs-1.8","title":"Investigating Code-Mixed Modern Standard Arabic-Egyptian to English Machine Translation","year":2021,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Machine translation; Computer science; Natural language processing; Artificial intelligence; Transformer; Arabic; Task (project management); Scratch; Language model; Code-switching; Context (archaeology); Code (set theory); Speech recognition; Programming language; Linguistics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002229891,0.00110121,0.0005778642,0.001057503,0.0008217985,0.001463465,0.0007255303,0.001047539,0.002911688],"category_scores_gemma":[0.008025512,0.0003566042,0.0005962469,0.001207847,0.0007025653,0.002142481,0.001363361,0.001417644,0.001669189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001178881,"about_ca_system_score_gemma":0.001259099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02054627,"about_ca_topic_score_gemma":0.02670184,"domain_scores_codex":[0.9988998,0.0004778969,0.00008646108,0.0002924489,0.0001429536,0.0001003766],"domain_scores_gemma":[0.9956637,0.002481045,0.0001881037,0.0005198114,0.0009505418,0.0001967837],"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":[0.002869252,0.001582391,0.05608971,0.001760823,0.000724378,0.002891017,0.003806663,0.3718408,0.0531114,0.01772263,0.0304178,0.4571832],"study_design_scores_gemma":[0.0001680509,0.0006236884,0.01060523,0.0001031393,0.0001413927,0.0006113417,0.001616697,0.9193828,0.04302461,0.008891849,0.01474338,0.00008787966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9356828,0.001147176,0.0460589,0.0008510721,0.0002383319,0.0001711716,0.001753233,0.003281108,0.01081609],"genre_scores_gemma":[0.9572093,0.0002455016,0.03193961,0.00028035,0.00004877731,0.0001205474,0.005337397,0.0003492167,0.004469377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02054627,"threshold_uncertainty_score":0.04085332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.020517177510522,"score_gpt":0.2739883452087444,"score_spread":0.2534711676982224,"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."}}