DEVELOPMENT OF AN ADDENDUM FOR THE FORMATION OF TEST QUESTIONS FROM THE GRAMMAR OF ENGLISH LANGUAGE BASED ON NEURAL TECHNOLOGIES
DOI:
https://doi.org/10.32782/tnv-tech.2023.4.5Keywords:
neural network technologies, application, text generation, distance learning, recurrent neural networkAbstract
The paper considers and compares different approaches to text generation using neural network methods. The goal is to choose the most optimal method for the task of generating short test sentences. In addition, a prototype of the application was created, which is capable of automatically creating test tasks in the English language. The research analyzed various approaches to text generation using neural networks. One possible direction is the use of recurrent neural networks, which are well suited for modeling sequential data. Another possible approach is to use transformers, such as GPT, which are able to learn long-term dependencies in the text. The task includes creating a program that will automatically create a variety of English grammar test tasks. For this, advanced methods of neural network modeling are used, which allow analyzing a large amount of linguistic data and learning grammatical rules. After a detailed analysis, the advantages and disadvantages of each approach were determined. The next step was the selection of the most suitable method for the task of generating short test sentences. After choosing a method, an application is developed that is capable of automatically creating English language test tasks based on the selected approach. The developed application is able to generate various tasks, such as filling gaps in sentences with correct grammatical constructions, translation from English to native language with correct use of grammar, and even more complex tasks related to analyzing the text for grammatical errors. This project has great potential in the educational field, helping teachers and students learn and understand English grammar more effectively. Automated creation of test tasks helps save time and effort when preparing training materials.
References
Zavgorodniy V.V., Yalova K.M. Technologies and software of e-learning system program implementation. Collection of scholarly papers of Dniprovsk State Technical University (Technical Sciences). 2016. Vol. 1 (28). P. 149–154.
Elsaadany A., Abbas K. Development and implementation of e-learning system in smart educational environment. 39th International Convention on Information and Communication Technology, Electronics and Microelectronics. 2016. P. 1004–1009. DOI: https://doi.org/10.1109/MIPRO.2016.7522286
Завгородній В.В., Ялова К.М. Перспективи використання дистанційної освіти для навчання IT-студентів у Дніпродзержинському державному технічному університеті. Вісник КрНУ імені Михайла Остроградського. 2015. Випуск 1 (90). Частина 2. С. 154–161.
Goldberg Y. Neural Network Methods for Natural Language Processing. Springer Cham. 2017. P. 292. ISBN 9783031021657. DOI: https://doi.org/10.1007/978-3-031-02165-7
Patil V., Jaware T., Badgujar R. Artificial Neural Network. LAP LAMBERT Academic Publishing. 2019. P. 52. ISBN-10 : 6200093415.
Tai Y., He H., Zhang W., Jia Y. Automatic Generation of Review Content in Specific Domain of Social Network Based on RNN. 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC). 2018. Р. 601–608.
Cho K., Merrienboer B.V., Gülçehre Ç., Bahdanau D., Bougares F., Schwenk H., Bengio Y. Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2014. P. 1724–1734. DOI: https://doi.org/10.3115/v1/D14-1179
Yoo J.Y,, John Morris J., Lifland E., Qi Y. Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples. In Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP. 2020. P. 323–332. https://doi.org/10.18653/v1/2020.blackboxnlp-1.30
