{"id":"W4416037652","doi":"10.18653/v1/2025.arabicnlp-main.10","title":"Lemmatizing Dialectal Arabic with Sequence-to-Sequence Models","year":2025,"lang":"","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Arabic; Feature (linguistics); Nasalization; Natural language","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":[0.0009187353,0.0008538084,0.0004071083,0.0008339448,0.0004327181,0.001600288,0.0007426469,0.0006454397,0.005023163],"category_scores_gemma":[0.004008438,0.0004029225,0.0009128146,0.0008047206,0.0005839248,0.002121022,0.00105669,0.001648652,0.005741135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007141853,"about_ca_system_score_gemma":0.001372699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005991579,"about_ca_topic_score_gemma":0.01410339,"domain_scores_codex":[0.9994149,0.0001938401,0.00004946197,0.0002033454,0.00009984858,0.00003864701],"domain_scores_gemma":[0.9981093,0.001067434,0.0001122797,0.0002756709,0.0003928806,0.00004238482],"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":[0.0006341235,0.0001856421,0.007972623,0.0005267507,0.0002509015,0.000984481,0.001369816,0.390781,0.04305152,0.04411205,0.02524328,0.4848878],"study_design_scores_gemma":[0.00001418268,0.00003708607,0.0004803623,0.000023912,0.00002526143,0.0001575123,0.0001891794,0.9538987,0.01129727,0.02361546,0.01024086,0.00002020685],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03839531,0.0003884344,0.94778,0.0004636441,0.000182495,0.0001343905,0.00189783,0.006396245,0.004361752],"genre_scores_gemma":[0.4611613,0.00062724,0.5168963,0.0005250329,0.0001365815,0.0002396922,0.01006826,0.001217091,0.009128561],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005991579,"threshold_uncertainty_score":0.0168041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03910445339087106,"score_gpt":0.3050145840558795,"score_spread":0.2659101306650085,"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."}}