Volume 13 - Issue 74
/ February 2024
299
http:// www.amazoniainvestiga.info ISSN 2322- 6307
DOI: https://doi.org/10.34069/AI/2024.74.02.25
How to Cite:
Yefymenko, T., Bilous, T., Zhukovska, A., Sieriakova, I., & Moyseyenko, I. (2024). Technologies for using interactive artificial
intelligence tools in the teaching of foreign languages and translation. Amazonia Investiga, 13(74), 299-307.
https://doi.org/10.34069/AI/2024.74.02.25
Technologies for using interactive artificial intelligence tools in the
teaching of foreign languages and translation
Технології Використання Інтерактивних Засобів Штучного Інтелекту у Викладанні
Іноземних Мов та Перекладу
Received: January 6, 2024 Accepted: February 27, 2024
Written by:
Tetiana Yefymenko1
https://orcid.org/0000-0002-7793-9505
Tamara Bilous2
https://orcid.org/0000-0001-7411-4623
Anna Zhukovska3
https://orcid.org/0000-0001-6636-610X
Iryna Sieriakova4
https://orcid.org/0000-0001-6446-7070
Iryna Moyseyenko5
https://orcid.org/0009-0009-5284-9376
Abstract
The article explores the potential of artificial
intelligence technologies in teaching foreign
languages and translation. It explores the
advantages and possible challenges of using such
technologies in language education and provides
practical examples. The article also discusses
perspectives on the future development and use
of interactive artificial intelligence tools in the
field of language teaching and translation. The
integration of artificial intelligence into higher
education has ushered in a new era of
transformation in educational processes,
reforming various aspects of the educational
experience. The advantages of introducing
artificial intelligence into higher education are
numerous, ranging from personalized learning
paths to intelligent assessment tools. The tools
are classified into categories for students,
1
Associate Professor, Candidate of philological sciences, Philological Faculty Department of Germanic Philology, Mykolaiv V.O.
Sukhomlynskyi National University, Mykolaiv, Ukraine.
2
Candidate of Pedagogical Sciences, Associate Professor, Department of English Practice and Methods of Teaching, Faculty of
Philology, Rivne State University of the Humanities, Rivne, Ukraine.
3
Candidate of Philological Sciences, Associate professor, Department of Fundamental and Special Disciplines, Novovolynsk
Education and Research Institute of Economics and Management of West Ukrainian National University, Novovolynsk, Ukraine.
4
Doctor of Philological Sciences, Professor, Professor of the Department of Philology and Translation, Kyiv National University of
Technologies and Design, Kyiv, Ukraine.
5
Candidate of Philological Sciences. Associate Professor, Associate Professor of the Department of Germanic and Finno-Ugric
Philology, Faculty of Germanic Philology and Translation, Kyiv National Linguistic University, Kyiv, Ukraine.
300
www.amazoniainvestiga.info ISSN 2322- 6307
teachers, and the education system. It identifies
key results of such processes and examines
various technologies, including Linguatech
Learning Assistant, Linguatech Translation Tool,
and Linguatech Language Lab, which help
students improve their language and translation
skills. The research examines the effectiveness of
interactive tools in education, comparing their
use in classroom and distance learning formats.
The article’s conclusions are significant for the
development and improvement of language and
translation education programs that use
innovative artificial intelligence technologies.
Keywords: identity, ethnicity, societal ideal,
state-building, national consciousness.
Introduction
Artificial intelligence is widely used in various
sectors of society, including the economy,
finance, marketing, medicine, industry, and
education. Machine learning reflects linguistic
intelligence in the context of artificial and human
intelligence. It is often confused or equated with
artificial intelligence. From a technical
perspective, machine learning is a subfield of
artificial intelligence. The primary objective of
artificial intelligence is to enable computers to
perform tasks that humans excel at, and learning
is one of the most critical skills in this regard.
Without the ability to learn, computers will not
be able to surpass humans eventually. Learning
enables the acquisition of new information,
which is then transformed into knowledge, skills,
and abilities. In conclusion, the highest
manifestation of intelligence in both humans and
machines is the ability to learn and acquire new
knowledge. However, the question remains open
as to how intelligent a machine can be compared
to a human, and how this intelligence can be
comparable or relative. Artificial intelligence is
an automated system or program that can
perform tasks characteristic of humans and make
optimal decisions based on the analysis of input
data. Artificial intelligence aims to
computationally model human thinking
processes by imitating cognitive functions of the
human brain. The ultimate goal is to replicate
these functions, creating a computational
component capable of achieving predefined
goals. Artificial intelligence can be classified into
several types, including Artificial Narrow
Intelligence (ANI), Artificial General
Intelligence (AGI), and Artificial Super
Intelligence (ASI). It is important to note that
tools such as ChatGPT are being used to aid in
learning English, providing students with access
to information, interactive teaching methods, and
individualization. The ASI, or Artificial
Superintelligence, is a theoretical type of AI that
is expected to possess exceptional intelligence
and surpass human cognitive abilities in solving
complex tasks. However, the creation of such a
superintelligence may have unpredictable
consequences, which is a topic of discussion
among researchers. In addition, universities are
exploring the impact of AI technologies on the
learning process and student development.
Interactive educational resources and virtual
learning environments can aid in the
development of students’ creativity,
independence, and learning efficiency. Some
popular technologies for learning English include
MyEnglishLab, Grammarly, Duolingo, Watson
Education, Memrise, and others. The use of
“speaking robots” provides ample opportunities
for speaking practice and independent work with
information resources, which can contribute to
personal growth and development.
Literature review
Modern requirements for higher education
students studying foreign languages, such as
English, establish a multifaceted system of skills,
including accurate pronunciation, grammar,
vocabulary, and style (Essel et al., 2024).
Students must be able to express their ideas
effectively in both written and spoken forms,
both online and offline. Learning a foreign
language at higher education institutions requires
advanced skills in understanding authentic
speech, including monological and dialogical
expressions (Hsu et al., 2023). Students should
be able to read original fiction, scientific, and
socio-political literature, interpret texts, and
Yefymenko, T., Bilous, T., Zhukovska, A., Sieriakova, I., Moyseyenko, I. / Volume 13 - Issue 74: 299-307 / February, 2024
Volume 13 - Issue 74
/ February 2024
301
http:// www.amazoniainvestiga.info ISSN 2322- 6307
participate in discussions on current topics from
various spheres of life in the foreign language.
Recent research and publications show a growing
interest in the project method among researchers.
The philosopher and educator John Dewey was
the first to introduce this method (Mogadala et
al., 2021). According to Dewey, project-based
learning promotes creativity and independent
thinking in students (Li et al., 2023). The project
method is a relevant scientific direction for
teaching foreign languages in both domestic and
foreign methodological science. This topic has
been studied by many Ukrainian and foreign
scholars, including Klimova et al. (2023). The
method encourages students to work semi-
autonomously and culminates in the creation of
real products or presentations. However,
language education using traditional methods
often encounters obstacles such as differences in
individual learning pace and limited
opportunities for practice and interaction
between teachers and students (Saichyshyna et
al., 2023). Artificial intelligence has become a
crucial factor in providing customized solutions
for individual students. AI-based tools can
analyse complex texts and offer insights on
grammar, vocabulary usage, and literary devices
(Yadlapally et al., 2023). The focus is on
interactive tools that enhance language learning
and develop speaking skills. It is worth noting
that interactive chatbots, online language
learning platforms, progress tracking systems,
automatic translation, and virtual assistants can
create an educational environment that stimulates
active learning and promotes language
competence growth. Additionally, researchers
are developing algorithms that can analyse
complex literary works and offer students a more
in-depth understanding of their “nuances” and
cultural context. Projects that utilize artificial
intelligence for foreign language and literature
learning offer vast potential (Chen et al., 2020).
They not only enhance students’ skills but also
advance artificial intelligence technologies.
However, it is important to consider major issues,
such as the use of artificial intelligence for
translation, which may impede students’
language competence development. Research
projects that focus on using artificial intelligence
for language learning have been shown to be
productive. This is because the learning process
becomes more individualized and adapted to
each student’s needs (Hasyim et al., 2021). Such
projects enable students to quickly understand
the use of artificial intelligence without
compromising their educational development.
Collaboration between educators, linguists,
artificial intelligence experts, and cultural
experts is crucial for the further development and
integration of these technologies into language
education (Chen et al., 2022). Studies attest to the
relevance and promising nature of using the
project method in teaching foreign languages,
which contributes to the development of both
general language skills and students’
professional competencies. Artificial intelligence
tools can facilitate language development by
providing students with personalized exercises
and educational materials for learning languages
online. These tools are classified based on
various criteria and are significant for improving
the processes of teaching and learning foreign
languages (Alam, 2021). Voice assistants, such
as Siri, Alexa, and Cortana, can be useful tools
for educators. They allow students to interact
more effectively with course materials and
receive necessary information instantly
(Yadlapally et al., 2023). These tools are
innovative and allow for the replacement of
traditional educational materials, making the
learning process more individualized. For
instance, Arizona State University has already
implemented an approach that enables students
to access necessary information independently at
any convenient moment. This facilitates their
learning and reduces pressure on educators,
thereby enhancing the quality of education (Sun
et al., 2021). Another tool that can be integrated
into higher education foreign language classes is
a chatbot. This program, based on machine
learning technology, can simulate real
conversation with the user and be used as an
assistant or translator for lectures and practical
materials for various audiences. ChatGPT,
developed by OpenAI laboratory (Mashtalir &
Nikolenko, 2023), is a popular artificial
intelligence tool.
The use of interactive artificial intelligence tools
in foreign language learning and translation has
significant potential for improving the quality of
education and increasing the effectiveness of the
learning process. Here are some technologies that
can be used in this field:
1. Language chatbots: Interactive chatbots
based on artificial intelligence can provide
students with opportunities to practice
language in real or simulated
communication situations. They can correct
errors, provide explanations, and help
students develop speaking and language
comprehension skills.
2. Online language learning platforms:
Platforms that use artificial intelligence can
adapt educational material to each student’s
needs, considering their level of knowledge,
individual requirements, and learning pace.
302
www.amazoniainvestiga.info ISSN 2322- 6307
They can also provide feedback and
recommendations for improving results.
3. Progress tracking systems: Artificial
intelligence-based tools can analyse
students’ results in real-time, track their
progress and weaknesses, and provide
personalized recommendations for further
learning.
4. Automatic translation systems: Machine
learning and deep learning technologies
allow for the creation of increasingly
accurate and fast automatic translation
systems, such as DeepL, Grammarly,
Instatext. These systems can be used for
translating texts, audio, and video materials,
facilitating understanding and mastery of
foreign languages.
5. Virtual language learning assistants: Virtual
assistants based on artificial intelligence can
provide interactive tasks, exercises, and
games for language learning. They can also
interact with students in dialogue form,
promoting active learning and memorization
of language constructs. These technologies
not only make the language learning process
more interesting and effective but also help
make it more accessible and flexible for
students with different needs and levels of
learning.
Methodology
The research methods used in this study involved
systematic and theoretical analysis of scientific
literature and language learning practices for
students. The approach included reviewing
existing scientific works and publications related
to the use of artificial intelligence (AI) in foreign
language education, both in Ukraine and abroad.
In addition, explanatory methods involved
synthesizing and effectively using acquired
knowledge to create and implement a research
project into the process of learning a foreign
language, using artificial intelligence. The
custom project for language learning with the
involvement of AI was developed within the
Python environment.
To investigate the effectiveness of the
Linguatech Learning Assistant app in learning
English, a random sample of 23 students was
gathered, consisting of 14 females and 9 males.
The participants either attended classroom
sessions (11) or used the app (12).
The study aimed to evaluate the success of
students depending on the learning format - in-
class or distance. To achieve this, a teaching
methodology with two levels - in-class and
distance learning - was created. Four types of
assessment were developed: quizzes, exams,
oral, and final assessments, to evaluate students’
knowledge.
The analysis used mixed-factor repeated
measures with two factors: teaching method and
assessment type. Paired samples t-tests were
conducted to determine which assessment tools
significantly differed between students learning
in-class and those in distance format.
To evaluate the overall difference in the average
success of students based on the teaching
method, we used a third variable - the average
grade point average (GPA) of the students - to
conduct an independent t-test.
Results and discussions
Project title: LINGUATECH: Innovative tools
for language teaching and translation.
Description: LINGUATECH is an innovative
project aimed at applying advanced artificial
intelligence technologies in the process of
foreign language teaching and translation. The
project develops and implements interactive
tools used by students, teachers and translators to
improve the efficiency of learning and working
with foreign languages.
Main components:
LINGUATECH Learning Assistant: An
interactive mobile application for learning
foreign languages. It uses artificial intelligence to
individualize the learning process, adapting
materials to the needs of each student, and
provides feedback and recommendations for
improving language skills.
Volume 13 - Issue 74
/ February 2024
303
http:// www.amazoniainvestiga.info ISSN 2322- 6307
Figure 1. Python code for the basic functionality of LINGUATECH Learning Assistant
This code creates a
‘LinguatechLearningAssistant’ class that can
store students’ progress in learning different
lessons, as well as recommend learning materials
based on the student’s target language.
LINGUATECH Translation Tool: A web-based
platform for translating texts using artificial
intelligence. It uses neural networks and machine
learning technologies to automatically translate
texts of varying complexity and specificity.
Figure 2. Python code for the basic functionality of LINGUATECH Translation Tool.
This code creates the class
‘LinguatechTranslationTool’, which can
translate text from the source language to the
target language. The `translate` function takes the
text to be translated and returns the translation
result in the specified language.
LINGUATECH Language Lab: An interactive
multimedia classroom for practical language
learning. It includes virtual communication
scenarios, gaming tasks, and real exercises for
developing language skills. Language Lab for
implementing simple operations in Python
language. Below is a general example.
```python
class LinguatechLearningAssistant:
def __init__(self, student_name, target_language):
self.student_name = student_name
self.target_language = target_language
self.learning_progress = {} # dictionary to store the progress of each student
def set_learning_progress(self, lesson, progress):
self.learning_progress[lesson] = progress
def get_learning_progress(self, lesson):
return self.learning_progress.get(lesson, "Progress is undefined")
def recommend_study_materials(self):
# Get recommendations for study materials
if self.target_language == 'English':
# return "Recommended book: English Grammar in Use"
elif self.target_language == 'Spanish':
return "Recommended book: ¡Hola Amigos!"
# Example of use
assistant = LinguatechLearningAssistant("Elena", "English")
assistant.set_learning_progress("Grammar", "Improved")
assistant.set_learning_progress("Vocabulary", "Needs improvement")
print(f "Olena's progress in grammar: {assistant.get_learning_progress('Grammar')}")
print(assistant.recommend_study_materials())
```
```python
class LinguatechTranslationTool:
def __init__(self, source_language, target_language):
self.source_language = source_language
self.target_language = target_language
def translate(self, text):
# Logic of text translation
translated_text = f"Текст '{text}' was translated from {self.source_language} into
{self.target_language}"
return translated_text
# Example of use
translator = LinguatechTranslationTool("English", "Ukrainian")
text_to_translate = "Hello, how are you?"
translation = translator.translate(text_to_translate)
print("Translation result:", translation)
```
304
www.amazoniainvestiga.info ISSN 2322- 6307
Figure 3. The software code for the basic functionality of LINGUATECH
In this example, a class
‘LinguatechLanguageLab’ is created, which
allows users to add words to the dictionary and
take quizzes. The ‘add_vocab_word’ function
adds words and their definitions to the dictionary,
while ‘take_quiz’ allows users to take a quiz with
questions and compares their answers with the
correct ones.
LINGUATECH provides students, teachers, and
translators with access to state-of-the-art
language learning and work technologies. The
platform’s effectiveness is demonstrated by
improvements in language proficiency, increased
productivity, and enhanced translation quality.
The study presents the results of an effectiveness
analysis of students’ learning using traditional
and interactive methods with a developed
application. The results are presented in the form
of mixed-factor repeated measures ANOVA with
two factors: teaching method (traditional
classroom vs. application) and assessment type
(quizzes, exams, oral, final).
The analysis revealed a significant main effect
for assessment type (F = 9.663, p = 0.000),
indicating the impact of the type of testing on
student performance. Significant differences
were identified among various types of
assessment, including quizzes, exams, oral, and
final (see Table 1).
Additionally, a significant main effect was
observed for the teaching method (F = 5.012, p =
0.031), confirming its impact on student success.
However, no interaction was found between
assessment types and teaching method (F =
1.232, p = 0.298).
Additional analyses did not reveal a significant
difference in performance between the traditional
classroom and the distance learning group (t = -
1.515, p = 0.137).
```python
class LinguatechLanguageLab:
def __init__(self, language):
self.language = language
self.vocab_list = {}
self.quiz_scores = {}
def add_vocab_word(self, word, definition):
self.vocab_list[word] = definition
def take_quiz(self, questions):
score = 0
for question in questions:
print(question)
user_answer = input("Your answer: ")
if user_answer.lower() == questions[question].lower():
print("Correct!")
score += 1
else:
print("Incorrect.")
self.quiz_scores[self.language] = score
print(f"Your score: {score}/{len(questions)}")
# Приклад використання
language_lab = LinguatechLanguageLab("Spanish")
language_lab.add_vocab_word("hola", "hello")
language_lab.add_vocab_word("adiós", "goodbye")
quiz_questions = {
"1. What does 'hola' mean?": "hello",
"2. What does 'adiós' mean?": "goodbye"
}
language_lab.take_quiz(quiz_questions)
```
Volume 13 - Issue 74
/ February 2024
305
http:// www.amazoniainvestiga.info ISSN 2322- 6307
Table 1.
Average Student Performance Depending on the Teaching Method
№
Assessment type
Audience
Extras
p
1
Quizzes
78,250
76,125
0,0000
2
Exams
82,375
76,000
0,0005
3
Oral
75,875
70,625
0,0031
4
Final
80,750
81,750
0,0035
These findings indicate that both teaching
methods can be effective in learning Spanish, but
they may impact different types of assessment in
varying ways.
The use of artificial intelligence tools for
language learning can be an effective solution to
address a range of issues, such as reducing
classroom hours and preparing qualified
professionals (Strobel et al., 2023). However,
alongside the implementation of such
innovations, it is important to develop certain
cognitive processes, such as perception, logical
thinking, memory, and imagination. There are
various types of artificial intelligence tools that
can be beneficial for language learning (Lytvyn
et al., 2023). Training tools provide students with
the opportunity to practice independently, check
their level of knowledge and skills, as well as
identify and correct their mistakes (Jackson et al.,
2024). Diagnostic tools help teachers monitor
and evaluate students’ level of learning
(Sabadash & Lysko, 2023). Communicative
tools, including dialogue with computers, can
assist students in overcoming communication
barriers and developing their language skills
(Vong et al., 2024). One way to improve
students’ language competence is the Content
and Language Integrated Learning (CLIL)
methodology, which is based on an integrated
interdisciplinary approach. It promotes
intercultural knowledge and creative thinking
and develops professional and general language
competencies (Kruger-Marais, 2024). An
interesting tool in the context of developing
intellectual linguistic resources is the translo- and
glotodidactic e-learning system
LISTiG13/LISST14 (Fiialka et al., 2023). This
intelligent tool was developed with the
participation of various organizations, including
university research units and recognized non-
university units with an international reputation
in the IT industry and linguistic tool
development. The LISST/LISTiG system is a
complex tool that combines translo- and
glotodidactic methods of e-learning. It provides
students with automatic feedback in response to
the information they input, including song lyrics.
After completing translation exercises, students
receive detailed feedback on their translated
sentences. The system also automatically
recognizes types of translation errors made and
provides information to students, allowing them
to correct mistakes. The instructor interface
allows students to familiarize themselves with
different translation options and associate error
messages with specific language phenomena.
The system also automatically evaluates inputted
texts in terms of grammar and spelling,
comparing them with correct translation variants
and sample answers previously entered by
instructors. Students receive automatic feedback
messages indicating errors in their translations
compared to sample answers. The system also
compares individual sentence parts entered by
students with corresponding information
previously entered into the system by the
instructor.
Tools that combine Translation Memory (TM)
and Machine Translation (MT) are known for
their high accuracy and effectiveness compared
to using either machine translation or translation
memory alone. These hybrid solutions are
gaining popularity due to their ability to optimize
translator workflow and improve translation
quality. The combination of both translation
support methods (TM+MT) leads to a significant
increase in correct translation matches. An
example of a hybrid approach is the Lilt program,
which uses an Intelligent Translation Memory
developed at Stanford University. The program
is designed for editing machine translation and
enhancing translation quality through systematic
self-learning. It provides translators with specific
advice based on their corrections, helping to
improve machine translation with each new
inputted text. Self-learning systems are gaining
popularity and effectiveness in the field of
translation. While most examples focus on
written translation, it is worth noting the rise of
intelligent speech recognition systems,
particularly in the context of spoken language.
Various tools, such as language bots, are capable
of conversing at a human level using different
strategies, including frequent topic changes and
evading questions.
Implementing this methodology into university
education may increase students’ motivation to
306
www.amazoniainvestiga.info ISSN 2322- 6307
learn English and focus their attention on
intercultural communication. However, there are
certain risks associated with using artificial
intelligence in language learning. Some students
may lack sufficient motivation and self-
discipline for effective online learning with
artificial intelligence. There is a risk that students
may rely too heavily on artificial intelligence
when completing tasks, which can hinder their
skill development and independence. Therefore,
it is important to develop verification tools that
can identify whether tasks were completed by
students independently or with the assistance of
artificial intelligence.
Conclusions
The significance and potential of artificial
intelligence technologies in foreign language
learning and translation have been demonstrated.
Research findings suggest that interactive AI
tools, such as Linguatech Learning Assistant,
Linguatech Translation Tool, and Linguatech
Language Lab, have a significant impact on
improving students’ language skills and
translation abilities. A crucial aspect of the study
is comparing the effectiveness of these tools in
both classroom and distance learning formats.
The results indicate that both teaching methods
can be effective. However, it is important to
consider their influence on different types of
assessment when developing and enhancing
educational programs. The article provides
compelling evidence of the effectiveness and
potential of using interactive AI tools in foreign
language teaching at Ukrainian higher education
institutions. The integration of artificial
intelligence in higher education presents new
opportunities for improving educational
processes and reforming various aspects of the
educational experience. This research represents
a significant step in the development and
enhancement of language learning and
translation programs through innovative artificial
intelligence technologies.
Bibliographic references
Alam, A. (2021, November). Possibilities and
apprehensions in the landscape of artificial
intelligence in education. In 2021
International Conference on Computational
Intelligence and Computing Applications
(ICCICA). IEEE. (pp. 1–8).
http://dx.doi.org/10.1109/ICCICA52458.202
1.9697272
Chen, L., Chen, P., & Lin, Z. (2020). Artificial
intelligence in education: A review. IEEE
Access, 8, 75264-75278.
https://doi.org/10.1109/ACCESS.2020.2988
510
Chen, X., Zou, D., Xie, H., Cheng, G., & Liu, C.
(2022). Two decades of artificial intelligence
in education. Educational Technology &
Society, 25(1), 28-47.
https://www.jstor.org/stable/48647028
Essel, H. B., Vlachopoulos, D., Essuman, A. B.,
& Amankwa, J. O. (2024). ChatGPT effects
on cognitive skills of undergraduate students:
Receiving instant responses from AI-based
conversational large language models
(LLMs). Computers and Education:
Artificial Intelligence, 6, 100198.
https://doi.org/10.1016/j.caeai.2023.100198
Fiialka, S., Kornieva, Z., & Honchar, T. (2023).
ChatGPT in Ukrainian Education: Problems
and Prospects. International Journal of
Emerging Technologies in Learning, 18(17).
https://doi.org/10.3991/ijet.v18i17.42215
Hasyim, M., Saleh, F., Yusuf, R., & Abbas, A.
(2021). Artificial Intelligence: Machine
Translation Accuracy in Translating French-
Indonesian Culinary Texts. International
Journal of Advanced Computer Science and
Applications, 12(3).
http://dx.doi.org/10.14569/IJACSA.2021.01
20323
Hsu, T. C., Chang, C., & Jen, T. H. (2023).
Artificial Intelligence image recognition
using self-regulation learning strategies:
effects on vocabulary acquisition, learning
anxiety, and learning behaviours of English
language learners. Interactive Learning
Environments, 1-19.
http://dx.doi.org/10.1080/10494820.2023.21
65508
Jackson, I., Jesus Saenz, M., & Ivanov, D.
(2024). From natural language to
simulations: applying AI to automate
simulation modelling of logistics
systems. International Journal of Production
Research, 62(4), 1434-1457.
https://doi.org/10.1080/00207543.2023.2276
811
Klimova, B., Pikhart, M., Benites, A. D.,
Lehr, C., & Sanchez-Stockhammer, C.
(2023). Neural machine translation in foreign
language teaching and learning: a systematic
review.
Education and Information
Technologies, 28(1), 663-682.
http://dx.doi.org/10.1007/s10639-022-
11194-2
Kruger-Marais, E. (2024). Subtitling for
language acquisition: Eye tracking as
predictor of attention allocation in
education. International Journal of
Volume 13 - Issue 74
/ February 2024
307
http:// www.amazoniainvestiga.info ISSN 2322- 6307
Language Studies, 18(2), 129-150.
https://zenodo.org/records/10475319
Li, P., Ning, Y., & Fang, H. (2023). Artificial
intelligence translation under the influence of
multimedia teaching to study English
learning mode. International Journal of
Electrical Engineering & Education, 60(2),
325-338.
https://doi.org/10.1177/0020720920983528
Lytvyn, V., Pukach, P., Vysotska, V., Vovk, M.,
& Kholodna, N. (2023). Identification and
Correction of Grammatical Errors in
Ukrainian Texts Based on Machine Learning
Technology. Mathematics, 11(4), 904.
https://doi.org/10.3390/math11040904
Mashtalir, S. V., & Nikolenko, O. V. (2023).
Data preprocessing and tokenization
techniques for technical Ukrainian
texts. Applied Aspects of Information
Technology, 6(3), 318-326.
https://aait.od.ua/index.php/journal/article/d
ownload/202/230/478
Mogadala, A., Kalimuthu, M., & Klakow, D.
(2021). Trends in integration of vision and
language research: A survey of tasks,
datasets, and methods. Journal of Artificial
Intelligence Research, 71, 1183-1317.
https://doi.org/10.48550/arXiv.1907.09358
Sabadash, V., & Lysko, V. (2023). Studies on
Adsorption of Petroleum Products under
Static Conditions. Journal of Ecological
Engineering, 24(10).
https://doi.org/10.12911/22998993/169997
Saichyshyna, N., Maksymenko, D., Turuta, O.,
Yerokhin, A., Babii, A., & Turuta, O. (2023).
Extension Multi30K: Multimodal Dataset for
Integrated Vision and Language Research in
Ukrainian. In Proceedings of the Second
Ukrainian Natural Language Processing
Workshop (UNLP) (pp. 54-61).
https://aclanthology.org/2023.unlp-1.7/
Strobel, G., Schoormann, T., Banh, L., &
Möller, F. (2023). Artificial Intelligence for
Sign Language Translation–A Design
Science Research Study. Communications of
the Association for Information Systems, 53,
42-64.
http://dx.doi.org/10.17705/1CAIS.05303
Sun, Z., Anbarasan, M., &
Praveen Kumar, D. J. C. I. (2021). Design of
online intelligent English teaching platform
based on artificial intelligence
techniques. Computational
Intelligence, 37(3), 1166-1180.
http://dx.doi.org/10.1111/coin.12351
Vong, W. K., Wang, W., Orhan, A. E., &
Lake, B. M. (2024). Grounded language
acquisition through the eyes and ears of a
single child. Science, 383(6682), 504-511.
https://doi.org/10.1126/science.adi1374
Yadlapally, D. K., Vasireddy, B.,
Marimganti, M., Chowdary, T.,
Karthikeyan, C., & Vignesh, T. (2023). A
Review on the Potential of AI Voice
Assistants for Personalized and Adaptive
Learning in Education. In 2023 7th
International Conference on Computing
Methodologies and Communication
(ICCMC). IEEE. (pp. 422-427).
http://dx.doi.org/10.1109/ICCMC56507.202
3.10084208