{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003150509,0.0001469579,0.0001702297,0.00008705942,0.0001190619,0.0003465377,0.0005541647,0.0000754025,0.0000252502],"category_scores_gemma":[0.0003235735,0.0001329183,0.00004720026,0.0006103221,0.00002140507,0.000636187,0.0001856053,0.0002076124,0.000006294347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005526964,"about_ca_system_score_gemma":0.0001333995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002512723,"about_ca_topic_score_gemma":0.0002421691,"domain_scores_codex":[0.9986044,0.00007596391,0.0002396525,0.000457703,0.0003724187,0.0002498273],"domain_scores_gemma":[0.9989141,0.0000671931,0.00005312723,0.0004606892,0.0003514298,0.0001535154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006092643,0.000029745,0.0003244261,0.00005264791,0.00001533972,0.00004000217,0.008344437,0.0002221591,0.04339094,0.05043365,0.001339206,0.8958014],"study_design_scores_gemma":[0.0004453726,0.0001070643,0.0001009914,0.000148491,0.00001045871,0.00002456293,0.00008767228,0.2913652,0.565033,0.1370685,0.005026141,0.0005826359],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004432905,0.001479593,0.9870638,0.002985763,0.0001805722,0.0001313579,0.000009701577,0.001399826,0.002316472],"genre_scores_gemma":[0.3823244,0.000002508849,0.6165081,0.0009568445,0.00004092767,0.000007680539,0.000008022374,0.000009353168,0.0001421812],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8952187,"threshold_uncertainty_score":0.5420251,"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."}}