MATNLARNI TO‘LDIRISH ALGORITMLARIDA QO‘LLANILADIGAN METODLARI

Bakayev I. I. & Abdunasimov S. S.


Annotatsiya

Mazkur maqolada tabiiy tilni qayta ishlash va mashinali o‘qitish tizimlarida ma’lumotlar yetishmasligi muammosini kamaytirishga yo‘naltirilgan matnlarni to‘ldirish algoritmlari tahlil qilingan. Ishning asosiy maqsadi matnni to‘ldirishga asoslangan metodlarni ilmiy-nazariy jihatdan tizimlashtirish hamda ularning qo‘llanish imkoniyatlarini baholashdan iborat. Maqolada sinonimlar asosida almashtirish, qisqartmalar bilan ishlash, so‘zlarni tasviriy va kontekstli fazoda almashtirish, teskari mashinaviy tarjima, shovqin kiritish hamda krossover yondashuvlarining ishlash tamoyillari ko‘rib chiqilgan. Metodlarning afzalliklari va cheklovlari semantik yaxlitlikni saqlash nuqtayi nazaridan tahlil qilingan. O‘tkazilgan tahlil natijalari matnlarni to‘ldirish algoritmlaridan foydalanish tasniflash modellarining barqarorligini oshirish, umumlashuv qobiliyatini yaxshilash hamda o‘quv ma’lumotlari xilma-xilligini ta’minlashga xizmat qilishini ko‘rsatadi. Olingan xulosalar tabiiy tilni qayta ishlashga oid amaliy tizimlarni ishlab chiqish va takomillashtirish jarayonlarida qo‘llanishi mumkin.


Adabiyotlar

  1. X. Zhang, J. J. Zhao, and Y. LeCun, “Character-level Convolutional Networks for Text Classification,” in NIPS, 2015, pp. 1–9. [Online]. Available: https://api.semanticscholar.org/CorpusID:368182
  2. B. Mengliyev, O. Xoliyorov, and N. Abdurahmanova, O‘zbek tilidan universal qo‘llanma. Toshkent: Akademiknashr, 2019.
  3. W. Y. Wang and D. Yang, “That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using {\#}petpeeve Tweets,” in Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal: Association for Computational Linguistics, 2015, pp. 2557–2563. doi: 10.18653/v1/D15-1306.
  4. M. Fadaee, A. Bisazza, and C. Monz, “Data Augmentation for Low-Resource Neural Machine Translation,” in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), Vancouver, Canada: Association for Computational Linguistics, 2017, pp. 567–573. doi: 10.18653/v1/P17-2090.
  5. S. Kobayashi, “Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations,” in Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), New Orleans, Louisiana: Association for Computational Linguistics, 2018, pp. 452–457. doi: 10.18653/v1/N18-2072.
  6. S. Garg and G. Ramakrishnan, “BAE: BERT-based Adversarial Examples for Text Classification,” ArXiv, vol. abs/2004.01970, 2020, [Online]. Available: https://api.semanticscholar.org/CorpusID:214802269
  7. Q. Xie, Z. Dai, E. H. Hovy, M.-T. Luong, and Q. V Le, “Unsupervised Data Augmentation for Consistency Training,” arXiv Learn., 2019, [Online]. Available: https://api.semanticscholar.org/CorpusID:195873898
  8. H. Chen and Y. Ji, “Improving the Explainability of Neural Sentiment Classifiers via Data Augmentation,” in 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 2019, pp. 1–11. [Online]. Available: https://api.semanticscholar.org/CorpusID:203951496
  9. J. Wei and K. Zou, “{EDA}: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks,” in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China: Association for Computational Linguistics, 2019, pp. 6382–6388. doi: 10.18653/v1/D19-1670.
  10. F. M. Luque, “Atalaya at TASS 2019: Data Augmentation and Robust Embeddings for Sentiment Analysis,” in IberLEF@SEPLN, 2019. [Online]. Available: https://api.semanticscholar.org/CorpusID:199448337