2 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 2 / 2
Yayın Evaluating the English-Turkish parallel treebank for machine translation(TÜBİTAK, 2022-01-19) Görgün, Onur; Yıldız, Olcay TanerThis study extends our initial efforts in building an English-Turkish parallel treebank corpus for statistical machine translation tasks. We manually generated parallel trees for about 17K sentences selected from the Penn Treebank corpus. English sentences vary in length: 15 to 50 tokens including punctuation. We constrained the translation of trees by (i) reordering of leaf nodes based on suffixation rules in Turkish, and (ii) gloss replacement. We aim to mimic human annotator's behavior in real translation task. In order to fill the morphological and syntactic gap between languages, we do morphological annotation and disambiguation. We also apply our heuristics by creating Nokia English-Turkish Treebank (NTB) to address technical document translation tasks. NTB also includes 8.3K sentences in varying lengths. We validate the corpus both extrinsically and intrinsically, and report our evaluation results regarding perplexity analysis and translation task results. Results prove that our heuristics yield promising results in terms of perplexity and are suitable for translation tasks in terms of BLEU scores.Yayın Psychometric properties of the Turkish version of the eating pathology symptoms inventory (EPSI-T)(Cogent OA, 2025) Türk, Fidan; Acet, Pınar; Karabulut, Goncagül; Akay, NazlıThe purpose of this study was to examine the factor structure and psychometric properties of the Turkish version of the Eating Pathology Symptoms Inventory (EPSI‑T), and to explore gender differences in eating disorder symptoms. Participants were 473 university students in Türkiye (342 women, 113 men) who completed the EPSI‑T, along with the Modified Weight Bias Internalization Scale (WBIS‑M), Addiction‑like Eating Behaviour Scale (AEBS), Muscularity‑Oriented Eating Test (MOET), and Depression Anxiety and Stress Scales (DASS‑21). Confirmatory factor analysis supported the original eight‑factor, 45‑item structure [χ2(914) = 1994.57, χ2/df = 2.18, CFI = 0.90, RMSEA = 0.05 (0.05–0.06), SRMR = 0.07]. Women scored significantly higher on most subscales, except for Excessive Exercise, Muscle Building, and Negative Attitudes toward Obesity, where men scored higher (p < 0.005). Reliability was strong, with Cronbach’s α ranging from 0.72 to 0.90 and McDonald’s ω from 0.75 to 0.90. Convergent and discriminant validity were also supported. Overall, findings suggest that the EPSI‑T is a reliable and valid measure of eating disorder symptoms in Turkish‑speaking populations and may facilitate cross‑cultural research by providing a tool structurally consistent with the original English version.
