3 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 3 / 3
Yayın Chunking in Turkish with conditional random fields(Springer-Verlag, 2015-04-14) Yıldız, Olcay Taner; Solak, Ercan; Ehsani, Razieh; Görgün, OnurIn this paper, we report our work on chunking in Turkish. We used the data that we generated by manually translating a subset of the Penn Treebank. We exploited the already available tags in the trees to automatically identify and label chunks in their Turkish translations. We used conditional random fields (CRF) to train a model over the annotated data. We report our results on different levels of chunk resolution.Yayın A tree-based approach for English-to-Turkish translation(Tubitak Scientific & Technical Research Council Turkey, 2019) Bakay, Özge; Avar, Begüm; Yıldız, Olcay TanerIn this paper, we present our English-to-Turkish translation methodology, which adopts a tree-based approach. Our approach relies on tree analysis and the application of structural modification rules to get the target side (Turkish) trees from source side (English) ones. We also use morphological analysis to get candidate root words and apply tree-based rules to obtain the agglutinated target words. Compared to earlier work on English-to-Turkish translation using phrase-based models, we have been able to obtain higher BLEU scores in our current study. Our syntactic subtree permutation strategy, combined with a word replacement algorithm, provides a 67% relative improvement from a baseline 12.8 to 21.4 BLEU, all averaged over 10-fold cross-validation. As future work, improvements in choosing the correct senses and structural rules are needed.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.
