Linguistic Resources and Transformer-based Models for the Machine Translations between Luri and Yazdi Dialects versus Standard Persian

Document Type : .

Authors
Zahra Bahmani 1
Mohaddeseh Mirbeygi 2
Negin Hashemi Dijujin 3
Marzieh Nouri 4
Mahsa Amani 5
Ehsan Asgari 6
Mahdieh Soleymani Baghshah 7
Hamid Beigy 7
Ali Movaghar 8
Afzal Moghimi 9
1 دانشجوی دکتری، دانشگاه صنعتی شریف، دانشکده مهندسی کامپیوتر، گروه هوش مصنوعی
2 PhD. Student, Department of Computer Engineering, Sharif University of Technology, AI Group
3 Msc. Student, Department of Computer Engineering, Sharif University of Technology, AI Group
4 Research Assistant, Language Processing and Digital Humanities Lab. , Sharif University of Technology
5 Bsc. Student, Department of Computer Engineering, Sharif University of Technology, AI Group
6 Qatar Computing Research Institute Engineering,
7 Associate Professor, Department of Computer Engineering, Sharif University of Technology, AI Group
8 Professor, Department of Computer Engineering, Sharif University of Technology, AI Group
9 Other
10.30465/lsi.2024.43456.1640
Abstract
Despite recent advances in developing language technologies for the standard Persian dialect, the official Iranian language, a large number of Iranian language variations remained computationally unexplored. Iranian languages, e.g., Kurdi, Azeri, and many Persian dialects are examples of low-resource language distinctions lacking significant linguistic resources such as machine-readable lexicons or part-of-speech (POS) taggers. Efforts in developing language technologies for such languages can significantly contribute to language survival in the digital era and promote cultural diversity. To the best of our knowledge, for the first time, we created linguistic resources for the Luri and the Yazdi dialects by introducing the first parallel corpora between these language variations and the modern Persian language. In this study, we train neural encoder-decoders (1) recurrent sequence-to-sequence and (2) transformer-based machine translation models and evaluate the trained model using BLEU score on an unseen test dataset.
Availability of datasets and models: Datasets are available here at https://github.com/language-ml/dataset_yazdi_luri.git

Keywords

Language and Linguistics
Volume 19, Issue 37
February 2024
Pages 153-172