{"id":"W2962724530","doi":"10.18653/v1/p17-2095","title":"Challenging Language-Dependent Segmentation for Arabic: An\\n Application to Machine Translation and Part-of-Speech Tagging","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Arabic; Computer science; Machine translation; Natural language processing; Artificial intelligence; Computational linguistics; Speech recognition; Segmentation; Volume (thermodynamics); Speech translation; Linguistics; Translation (biology); Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001061876,0.00007819508,0.00008282026,0.00006090035,0.0001958482,0.0001838307,0.0004353872,0.00004390111,0.00008228033],"category_scores_gemma":[0.0001322027,0.00007552477,0.00001826717,0.00004002949,0.000003145813,0.0006659019,0.00008385035,0.00004611645,0.000004699321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001671499,"about_ca_system_score_gemma":0.00001063445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001764716,"about_ca_topic_score_gemma":0.00003572926,"domain_scores_codex":[0.9993991,0.00001158562,0.0001168812,0.0002413644,0.0001238083,0.0001072359],"domain_scores_gemma":[0.9993237,0.00003807685,0.0001471706,0.0003718823,0.00007504589,0.00004409355],"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":[0.000005535529,0.000008510193,0.000009800731,0.0001351341,0.000002853179,0.000001154197,0.00115598,0.00001716752,0.008174047,0.0002507597,0.0002110855,0.990028],"study_design_scores_gemma":[0.0008327453,0.0002877002,0.0004557497,0.001457887,0.00001631202,0.00002070667,0.0001538321,0.5282848,0.4578005,0.003586703,0.006498848,0.0006042412],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00133014,0.003888492,0.9822289,0.001473662,0.0000682087,0.001512719,0.008731683,0.0005674298,0.0001987182],"genre_scores_gemma":[0.7098134,0.000003523427,0.2863442,0.00008894048,0.00007926578,0.0002871108,0.003356338,0.0000118615,0.00001532374],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9894238,"threshold_uncertainty_score":0.307981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04363071102748368,"score_gpt":0.3350684569612692,"score_spread":0.2914377459337856,"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."}}