BUILDING A PARALLEL LEXICON FOR TRANSLATING THE KHOREZMIAN UZBEK DIALECT INTO STANDARD UZBEK
Raximbayeva M. D., Kurbanova L. U., Ramatova Z. Z., Shamuratova R. R. & Sa’dullayeva B. H.
Annotatsiya
Xorazm o‘zbek shevasi leksik, fonetik va morfologik jihatdan adabiy o‘zbek tilidan sezilarli darajada farq qiladi, bu esa shevaga oid matnlarni avtomatik qayta ishlash va tarjima qilishni murakkablashtiradi. Mavjud tarjima va normallashtirish tizimlari uchun zarur bo‘lgan tuzilmaviy til resurslarining yetishmasligi ushbu sohada muhim muammo hisoblanadi. Ushbu tadqiqotda Xorazm shevasini adabiy o‘zbek tiliga o‘girishni qo‘llab-quvvatlovchi parallel lug‘atni ishlab chiqish masalasi ko‘rib chiqiladi.Taklif etilgan lug‘at Xorazm shevasidagi so‘z shakllari va ularning adabiy o‘zbek tilidagi muqobillarini autentik og‘zaki va yozma manbalar asosida yig‘ish va moslashtirish orqali yaratildi. Resurs shevaga xos bo‘lgan fonetik o‘zgarishlar, morfologik variantlar va leksik tafovutlarni qamrab oladi hamda har bir birlik uchun mos adabiy shaklni taqdim etadi. Parallel lug‘atning amaliy samaradorligini baholash maqsadida u dialekt-adabiy til o‘girish tizimiga integratsiya qilinib, Xorazm shevasidagi gaplar to‘plamida sinovdan o‘tkazildi. Natijalar lug‘atdan foydalanish tarjima aniqligini sezilarli darajada oshirishi va ayniqsa morfologik hamda leksik xatolarni kamaytirishini ko‘rsatdi. Yaratilgan resurs Xorazm shevasi uchun muhim lingvistik asos bo‘lib, kelgusida dialektlarni normallashtirish, korpuslar yaratish va neyron tarjima tizimlarini rivojlantirish uchun mustahkam poydevor vazifasini bajaradi.
Adabiyotlar
- Kompyuter lingvistikasi va neyrotarjima asoslari (Foundational Works) Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python. O’Reilly Media.
- Jurafsky, D., & Martin, J. H. (2023). Speech and Language Processing (3rd ed. draft). Stanford University.
- Koehn, P. (2020). Neural Machine Translation. Cambridge University Press. Lample, G., et al. (2018). Phrase-based & neural unsupervised machine translation. Proceedings of EMNLP, 5039–5049.
- Shevalarni qayta ishlash va normalashtirish (Dialect Processing & Normalization)
- Bouamor, H., Habash, N., & Oflazer, K. (2018). A survey on Arabic dialect processing. Computational Linguistics, 44(3), 1–44.
- Huckvale, K., & Habash, N. (2019). Leveraging lexicons for dialect-to-standard normalization. Proceedings of the Workshop on NLP for Similar Languages, Varieties and Dialects, 33–42.
- Orhun, O., & Tantuğ, A. C. (2019). Dialect identification and normalization for Turkish. Natural Language Engineering, 25(3), 379–402.
- Tantuğ, A. C., & Adalı, E. (2018). Machine translation between standard Turkish and regional dialects. Proceedings of the Workshop on NLP for Similar Languages, 72–80.
- Morfologiya va so‘z yasalishi tahlili (Morphological Analysis) Cotterell, R., Müller, M., & Schütze, H. (2016). Morphological segmentation inside-out. Proceedings of EMNLP, 232–237.
- Creutz, M., & Lagus, K. (2005). Unsupervised morpheme segmentation and morphology induction. ACL Workshop, 47–54.
- Habash, N., Eskander, R., & Hawwari, A. (2012). A morphological analyzer for Egyptian Arabic. Proceedings of NAACL-HLT, 1–10.
- Kann, K., & Schütze, H. (2016). Single-model encoder-decoder with explicit morphological representation. Proceedings of ACL, 555–560.
- Oflazer, K., & El-Kahlout, I. D. (2007). Exploring different representational units in English-to-Turkish statistical machine translation. Proceedings of ACL, 458–465.
- O‘zbek tili va shevalari bo‘yicha tadqiqotlar (Uzbek Language Specific Research) Abdurakhmonova, N., Sharipov, M., & Salayev, U. (2024). Building lexical resources for Uzbek dialect normalization. Proceedings of Regional NLP Workshop, 15–22.
- Sharipov, M., & Salayev, U. (2023). Issues of automatic processing of Uzbek dialectal texts. Khorezm Science Journal, 2(1), 45–52.
- Zulfikarov, F. (2021). O‘zbek shevalarining lingvistik xususiyatlari. O‘zbek tili va adabiyoti, 4, 56–63.
- Ma’lumotlar bazasi va baholash usullari (Resources & Evaluation) Popović, M. (2015). chrF: character n-gram F-score for automatic MT evaluation. Proceedings of the Tenth Workshop on Statistical Machine Translation, 392–395.
- Sennrich, R., Haddow, B., & Birch, A. (2016). Neural machine translation of rare words with subword units. Proceedings of ACL, 1715–1725.
- Tiedemann, J. (2012). Parallel data, tools and interfaces in OPUS. Proceedings of LREC, 2214–2218.
- Zeman, D., et al. (2018). Universal Dependencies 2.0 – A multilingual treebank collection. Proceedings of LREC, 181–188.