Neural dependency parsing for Turkish
Is this your thesis?
This record came from a bulk archive import. If it’s yours, link it to your profile.
Abstract (EN)
Dependency Parsing is the task of finding the grammatical structure of a sentence by identify- ing syntactic and semantic relationships between words. The current accuracy of the depen- dency parsers is still not satisfying due to the long term dependencies and out-of-vocabulary (OOV) problem. Those problems also apply to Turkish because of the high percentage of OOV words due to its agglutinative morphological structure compared to other languages. The recent work shows that Recurrent Neural Networks (RNNs) are not efficient for long sequences. The deep neural architecture that we propose in this thesis follows an encoder- decoder structure with an encoder based on a Transformer Network and a decoder based on a Stack Pointer Network. The character-level word embeddings are also integrated in the model to cope with the OOV problem. The results for both Turkish and English show that the proposed model performs better for long sentences and can identify long term dependencies more efficiently compared to other neural models.
Author
Salih Tuç
How to Cite
Salih Tuç (Master Thesis). Neural dependency parsing for Turkish, 2020, Hacettepe University.
Keywords
EN
License
Tüm Hakları Saklıdır
This work is shared under the specified license terms.
More theses from Hacettepe University
- A critical evaluation of pronunciation teaching in an ELT department in Turkey(2023)
- Gençlerin ve Gençlik Çalışanlarının Gözünden Gençlik Politikaları ve Hizmetlerinin Değerlendirilmesi(2022)
- Çağdaş kamu yönetiminde enformasyon teknolojisinin yeri ve enformasyon sistemleri(2026)
- Neoliberalism and transformation of the state in Turkey: An analysis on the two-nations hegemonic project(2018)
- Evaluation of phonological memory and visuo-spatial sketchpad in children who stutter(2018)
- Investigation of the effect of central vestibular dysfunction on physical functionality and cognitive function in patients with ambulatory multiple sclerosis(2024)
