{"id":"W4385573074","doi":"10.18653/v1/2022.emnlp-demos.32","title":"Camelira: An Arabic Multi-Dialect Morphological Disambiguator","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Arabic; Computer science; Component (thermodynamics); Modern Standard Arabic; Natural language processing; Identification (biology); Interface (matter); Artificial intelligence; 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":[0.0007778714,0.001469542,0.0008517003,0.002841208,0.001055453,0.001874889,0.00189266,0.001177004,0.02048691],"category_scores_gemma":[0.002278312,0.0007329657,0.001049449,0.0008970961,0.000452312,0.003162276,0.003246943,0.00104852,0.02202927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004646117,"about_ca_system_score_gemma":0.0006763106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001246799,"about_ca_topic_score_gemma":0.001903075,"domain_scores_codex":[0.9993014,0.00007863423,0.00008887299,0.0002701185,0.0002088797,0.00005213654],"domain_scores_gemma":[0.9992437,0.0001706158,0.0000858023,0.0001547747,0.0002507801,0.00009437696],"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":[0.001512238,0.0002410913,0.005076025,0.001335341,0.0002577114,0.001910133,0.001294697,0.001571173,0.1188405,0.01095167,0.261666,0.5953434],"study_design_scores_gemma":[0.0003055861,0.0002461824,0.00535588,0.0002684216,0.0002229803,0.0048311,0.0005948216,0.03957583,0.1534178,0.01104301,0.7838035,0.0003348809],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02931852,0.002152048,0.4852138,0.0006456869,0.001096615,0.0004364692,0.01665913,0.4375099,0.02696785],"genre_scores_gemma":[0.1132195,0.0006380851,0.8132778,0.001289248,0.0003229898,0.0003682614,0.03344131,0.01594079,0.02150201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02048691,"threshold_uncertainty_score":0.06853557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02902459647331002,"score_gpt":0.2951499694393067,"score_spread":0.2661253729659967,"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."}}