دانشگاه تربیت دبیر شهید رجائی

  اخبار و اعلانات

 آمار

تعداد نشریات13
تعداد شماره‌ها200
تعداد مقالات2,008
تعداد مشاهده مقاله2,680,170
تعداد دریافت فایل اصل مقاله1,937,363
Soluki, M., Askarinejadamiri, Z., Zanjani, N.. (1402). Using GPT-2 Model and Hazm Library for Persian Text Generation. فناوری آموزش, (), 295-304. doi: 10.22061/jecei.2023.10101.690
M. Soluki; Z. Askarinejadamiri; N. Zanjani. "Using GPT-2 Model and Hazm Library for Persian Text Generation". فناوری آموزش, , , 1402, 295-304. doi: 10.22061/jecei.2023.10101.690
Soluki, M., Askarinejadamiri, Z., Zanjani, N.. (1402). 'Using GPT-2 Model and Hazm Library for Persian Text Generation', فناوری آموزش, (), pp. 295-304. doi: 10.22061/jecei.2023.10101.690
Soluki, M., Askarinejadamiri, Z., Zanjani, N.. Using GPT-2 Model and Hazm Library for Persian Text Generation. فناوری آموزش, 1402; (): 295-304. doi: 10.22061/jecei.2023.10101.690

Using GPT-2 Model and Hazm Library for Persian Text Generation

Journal of Electrical and Computer Engineering Innovations (JECEI)
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 04 دی 1402
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2023.10101.690
نویسندگان
M. Soluki؛ Z. Askarinejadamiri* ؛ N. Zanjani
Computer science of Refah University college, Tehran, Iran.
تاریخ دریافت: 19 شهریور 1402،  تاریخ بازنگری: 27 آذر 1402،  تاریخ پذیرش: 04 دی 1402 
چکیده
Background and Objectives: This article explores a method for generating Persian texts using the GPT-2 language model and the Hazm library. Researchers and writers often require tools that can assist them in the writing process and even think on their behalf in various domains. By leveraging the GPT-2 model, it becomes possible to generate acceptable and creative texts, which increases writing speed and efficiency, thus mitigating the high costs associated with article writing.
Methods: In this research, the GPT-2 model is employed to generate and predict Persian texts. The Hazm library is utilized for natural language processing and automated text generation. The results of this study are evaluated using different datasets and output representations, demonstrating that employing the Hazm library with input data exceeding 1000 yields superior outcomes compared to other text generation methods
Results: Through extensive experimentation and analysis, the study demonstrates the effectiveness of this combination in generating coherent and contextually appropriate text in the Persian language. The results highlight the potential of leveraging advanced language models and linguistic processing tools for enhancing natural language generation tasks in Persian. The findings of this research contribute to the growing field of Persian language processing and provide valuable insights for researchers and practitioners working on text generation applications in similar languages.
Conclusion: Overall, this study showcases the promising capabilities of the GPT-2 model and Hazm library in Persian text generation, underscoring their potential for future advancements in the field This research serves as a valuable guide and tool for generating Persian texts in the field of research and scientific writing, contributing to cost and time reduction in article writing
کلیدواژه‌ها
Persian text genertion؛ Hazm Library؛ GPT-2 Model
مراجع

[1] D. McDonald, P. Proctor, W. Gill, S. Heaven, J. Marr, J. Young, "Increasing early childhood educators’ use of communication-facilitating and language-modelling strategies: Brief speech and language therapy training," Child Lang. Teach. Ther., 31(3): 305-322, 2015.

[2] E. S. Jo, T. Gebru, "Lessons from archives: Strategies for collecting sociocultural data in machine learning," in Proc. the 2020 Conference on Fairness, Accountability and Transparency: 306-316 2020.

[3] P. P. Ray, "ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope," Internet Things Cyber-Phys. Syst., 3: 121-154, 2023.

[4] A. Tamkin, M. Brundage, J. Clark, D. Ganguli, "Understanding the capabilities, limitations, and societal impact of large language models," arXiv preprint arXiv:2102.02503, 2021.

[5] Y. Yibin, C. Na, X. Chaoqian, Y. Junjian, "Accuracy assessment and analysis for GPT2," Acta Geod. Cartographica Sin., 44(7):726, 2015.

[6] A. S. George, A. H. George, "A review of ChatGPT AI's impact on several business sectors," Partners Univers. Int. Innovation J., 1(1): 9-23, 2023.

[7] X. Zheng, C. Zhang, P. C. Woodland, "Adapting GPT, GPT-2 and BERT language models for speech recognition," in Proc. 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU): 162-168, 2021.

[8] Z. Liu, R. A. Roberts, M. Lal-Nag, X. Chen, R. Huang, W. Tong, "AI-based language models powering drug discovery and development," Drug Discovery Today, 26(11): 2593-2607, 2021.

[9] N. De Cao, T. Kipf, "MolGAN: An implicit generative model for small molecular graphs," arXiv preprint arXiv:1805.11973, 2018.

[10] M. Mars, "From word embeddings to pre-trained language models: A state-of-the-art walkthrough," Appl. Sci., 12(17): 8805, 2022.

[11] Y. Qu, P. Liu, W. Song, L. Liu, M. Cheng, "A text generation and prediction system: pre-training on new corpora using BERT and GPT-2," in Proc. 2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC): 323-326, 2020.

[12] O. Shatalov, N. Ryabova, "Towards Russian text generation problem using OpenAI’s GPT-2," in Proc. CEUR Workshop 2021.

[13] N. Alexandr, O. Irina, K. Tatyana, K. Inessa, P. Arina, "Fine-tuning gpt-3 for russian text summarization," in Data Science and Intelligent Systems: Proceedings of 5th Computational Methods in Systems and Software, 2: 748-757, 2021.

[14] T. Goyal, J. J. Li, G. Durrett, "News summarization and evaluation in the era of gpt-3," arXiv preprint arXiv:2209.12356, 2022.

[15] S. Kumari, T. Pushphavati, "Question answering and text generation using BERT and GPT-2 model," in Proc. ICCMDE 2021 Computational Methods and Data Engineering: 93-110, 2022.

[16] A. H. George, A. S. Hameed, A. S. George, T. Baskar, "Study on quantitative understanding and knowledge of farmers in trichy district," Partners Univer. Int. Res. J., 1(2): 5-8, 2022.

[17] J. Devlin, M. W. Chang, K. Lee, K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding," arXiv preprint arXiv:1810.04805, 2018.

[18] A. Kraft, "Triggering models: Measuring and mitigating bias in german language generation," Universität Hamburg, 2021.

[19] M. Moila, T. Modipa, J. Manamela, "The analysis of a GPT-based Sepedi text generation model," in Proc. International Conference on Intelligent and Innovative Computing Applications: 144-152, 2022.

[20] S. P. Ramalepe, T. I. Modipa, M. H. Davel, “The development of a sepedi text generation model using transformers,” in Proc. Southern Africa Telecommunication Networks and Applications Conference (SATNAC)," 2022.

[21] L. Butgereit, A. van Staden, "Supporting home-language education in africa with multi-lingual mathematics tutoring using GPT-4," in Proc. International Conference on Artificial Intelligence and its Applications: 44-49, 2023.

[22] S. Yang, D. Feng, L. Qiao, Z. Kan, D. Li, "Exploring pre-trained language models for event extraction and generation," in Proc. the 57th Annual Meeting of the Association for Computational Linguistics: 5284-5294, 2019.

[23] J. Mellon, J. Bailey, R. Scott, J. Breckwoldt, M. Miori, " Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale," SSRN Electron. J., 2022.

[24] A. Radford et al., "Better language models and their implications. OpenAI," ed, 2019.

[25] R. Dale, "GPT-3: What’s it good for?," Nat. Lang. Eng., 27(1): 113-118, 2021.

[26] M. Zhang, J. Li, "A commentary of GPT-3 in MIT Technology Review 2021," Fundam. Res., 1(6): 831-833, 2021.

[27] B. Zhu, Z. Gu, Y. Qian, F. Lau, Z. Tian, "Leveraging transferability and improved beam search in textual adversarial attacks," Neurocomputing, 500: 135-142, 2022.

[28] D. Kim, J. Lee, "Designing an algorithm-driven text generation system for personalized and interactive news reading," Int. J. Human–Computer Interact., 35(2): 109-122, 2019.

[29] X. He et al., "Cater: Intellectual property protection on text generation apis via conditional watermarks," Adv. Neural Inf. Process. Syst., 35: 5431-5445, 2022.

[30] J. Li, Z. Li, L. Mou, X. Jiang, M. Lyu, I. King, "Unsupervised text generation by learning from search," Adv. Neural Inf. Process. Sys., 33: 10820-10831, 2020.

آمار
تعداد مشاهده مقاله: 330


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب