{"id":"W2134830997","doi":"10.7202/029804ar","title":"Constructing a Large-Scale English-Persian Parallel Corpus","year":2009,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Payame Noor University; University of Warwick","keywords":"Persian; Computer science; Natural language processing; Machine translation; Task (project management); Artificial intelligence; The Internet; String (physics); Scale (ratio); Software; Corpus linguistics; Construct (python library); Linguistics; World Wide Web; Information retrieval; Programming language; Engineering; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008283792,0.0002566303,0.0003986341,0.0002245005,0.0004054366,0.000721198,0.001367487,0.00009159388,0.00003010038],"category_scores_gemma":[0.0002443817,0.0001987498,0.0002830541,0.0005660899,0.0001081056,0.001467499,0.00007313997,0.0007369664,0.000006026507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000983804,"about_ca_system_score_gemma":0.00007506624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003535957,"about_ca_topic_score_gemma":0.000007623712,"domain_scores_codex":[0.9980418,0.0001765453,0.0003955943,0.0003652335,0.0004336668,0.0005871347],"domain_scores_gemma":[0.9987377,0.0000607363,0.0002608532,0.0003985623,0.0002850863,0.0002570898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002206191,0.00015183,0.0006640148,0.00002059175,0.0002400862,0.0004544092,0.003145623,0.00001411632,0.002284918,0.1227731,0.001120553,0.8691087],"study_design_scores_gemma":[0.002068536,0.0008681336,0.0012294,0.0002406621,0.0007160194,0.01464781,0.0008015414,0.0043442,0.03113855,0.9068347,0.03545055,0.001659853],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.010471,0.05785197,0.9281372,0.001373464,0.0006340322,0.0001134575,0.000003107741,0.0006358011,0.0007799217],"genre_scores_gemma":[0.1545735,0.0007471592,0.8436326,0.0006038817,0.0002822864,0.000002547767,0.000001285374,0.00001409068,0.0001426034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8674488,"threshold_uncertainty_score":0.8104783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01813183722996285,"score_gpt":0.2598321190240259,"score_spread":0.2417002817940631,"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."}}