A novel hybrid algorithm for morphological analysis: artificial Neural-Net-XMOR
Yazarlar (3)
Dr. Öğr. Üyesi Ayla KAYABAŞ
Kırşehir Ahi Evran Üniversitesi, Türkiye
Ahmet E. Topcu
American University Of The Middle East, Kuveyt
Özkan Kiliç
Cisco Systems, Amerika Birleşik Devletleri
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Turkish Journal of Electrical Engineering and Computer Sciences (Q4) | ||
| Dergi ISSN | 1300-0632 Wos Dergi Scopus Dergi | ||
| Dergi Tarandığı Indeksler | SCI-Exp, SCOPUS, Curation, Essential Science Indicators, Pdf2xml, Pdf2xml, Reference Master, Sophia, Web Of Science Expanded | ||
| Makale Dili | İngilizce | Basım Tarihi | 01-2022 |
| Cilt / Sayı / Sayfa | 30 / 5 / 1726–1740 | DOI | 10.55730/1300-0632.3901 |
| Makale Linki | https://journals.tubitak.gov.tr/cgi/viewcontent.cgi?article=3901&context=elektrik | ||
| Özet |
| In this study, we present a novel algorithm that combines a rule-based approach and an artificial neural network-based approach in morphological analysis. The usage of hybrid models including both techniques is evaluated for performance improvements. The proposed hybrid algorithm is based on the idea of the dynamic generation of an artificial neural network according to two-level phonological rules. In this study, the combination of linguistic parsing, a neural network-based error correction model, and statistical filtering is utilized to increase the coverage of pure morphological analysis. We experimented hybrid algorithm applying rule-based and long short-term memory-based (LSTM-based) techniques, and the results show that we improved the morphological analysis performance for optical character recognizer (OCR) and social media data. Thus, for the new hybrid algorithm with LSTM, the accuracy reached 99.91% for the OCR dataset and 99.82% for social media data. |
| Anahtar Kelimeler |
| Algorithm | artificial neural network | hybrid model | morphology | rule-based system |
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| WoS | 2 |
| SCOPUS | 2 |
| TRDizin | 1 |
| Google Scholar | 3 |