Filtreler

20192
Filtreleri Sıfırla

Ayarlar

Yazar: Avar, Begüm × Konu: Computational linguistics ×

Arama Sonuçları

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Yayın
    A tree-based approach for English-to-Turkish translation
    (Tubitak Scientific & Technical Research Council Turkey, 2019) Bakay, Özge; Avar, Begüm; Yıldız, Olcay Taner
    In 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.
  • Küçük Resim
    Yayın
    An open, extendible, and fast Turkish morphological analyzer
    (Incoma Ltd, 2019-09) Yıldız, Olcay Taner; Avar, Begüm; Ercan, Gökhan
    In this paper, we present a two-level morphological analyzer for Turkish which consists of five main components: finite state transducer, rule engine for suffixation, lexicon, trie data structure, and LRU cache. We use Java language to implement finite state machine logic and rule engine, Xml language to describe the finite state transducer rules of the Turkish language, which makes the morphological analyzer both easily extendible and easily applicable to other languages. Empowered with a comprehensive lexicon of 54,000 bare-forms including 19,000 proper nouns, our morphological analyzer is amongst the most reliable analyzers produced so far. The analyzer is compared with Turkish morphological analyzers in the literature. By using LRU cache and a trie data structure, the system can analyze 100,000 words per second, which enables users to analyze huge corpora in a few hours.