QAYTA SOZLANGAN TRANSFORMER MODELLAR YORDAMIDA INGLIZCHA-O‘ZBEKCHA MASHINA TARJIMASINI TAKOMILLASHTIRISH
Ключевые слова:
Katta til modellari, Hugging Face, Mashina tarjimasi, Generative Pretrained Transformers, Tabiiy tilni qayta ishlashАннотация
Tabiiy tilga tegishli matnlarni aniq va sifatli tarjima qilish vazifasi
tabiiy tilga ishlov berishning (NLP) o‘ta muhim vazifalaridan biri hisoblanadi.
Mashinaviy o‘rganish yordamida aniq va tez amalga oshiriladigan avtomatlashtirilgan
tarjima ko‘pincha mashinaviy o‘rganish va sun’iy intellekt fanlari hamjamiyatlarida
katta qiziqish uyg‘otadi. Ushbu tadqiqot doirasida mashina tarjimasini amalga oshirish
uchun o’zbek tilining mahalliy internet manbaalaridan, kitob, darslik va ilmiy ishlardan
yig’ilgan matnlarning parallel korpusi yordamida Generative Pretrained Transformer
(GPT) modellaridan foydalanishni ko‘rib chiqamiz. Biz Hugging Face katta til
modellari (LLM) ro’yxatidagi o’zbek tili uchun o’qitilgan 2 xil modelni qayta sozlash
orqali mashina tarjimasini amalga oshirish va ularning turli xil metrikalar bo’yicha
tarjima sifatining baholarini qiyosiy tahlil qilamiz. Tanlangan modellarni sozlash
Google colab muhitida A100 Grafikani qayta ishlash bloki (GPU) yordamida amalga
oshirilgan.
Библиографические ссылки
1.
Amilia, Ika & Yuwono, Darmawan. (2020). A study of the translation of google
translate. Lingua : jurnal ilmiah. 16. 1-21. 10.35962/lingua.v16i2.50.
2.
Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky,
Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav
Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard
Grave, Michael Auli, and Armand Joulin. 2021. Beyond english-centric multilingual
machine translation. J. Mach. Learn. Res. 22, 1, Article 107 (January 2021), 48 pages.
3.
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones,
Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need.
In Proceedings of the 31st International Conference on Neural Information Processing
Systems (NIPS'17). Curran Associates Inc., Red Hook, NY, USA, 6000–6010.
4.
Jörg Tiedemann and Santhosh Thottingal. 2020. OPUS-MT – Building open
translation services for the World. In Proceedings of the 22nd Annual Conference of
the European Association for Machine Translation, pages 479–480, Lisboa, Portugal.
European Association for Machine Translation.
5.
Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a
Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th
Annual Meeting of the Association for Computational Linguistics, pages 311–318,
Philadelphia, Pennsylvania, USA. Association for Computational Linguistics.
6.
Liu et al., "Multilingual Denoising Pre-training for Neural Machine
Translation", 2020.
7.
Robert Östling, Yves Scherrer, Jörg Tiedemann, Gongbo Tang, and Tommi
Nieminen. 2017. The Helsinki Neural Machine Translation System. In Proceedings of
