English-Chinese Machine Translation Model Based on Bidirectional Neural Network with Attention Mechanism

Li, Yonglan; Wenjia, He

doi:10.1155/2022/5199248

Cited by 12 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, translators proficient in both languages play a vital role in bridging linguistic and cultural gaps in our increasingly diverse and interconnected world. The design and application of an English-Chinese bilingual teaching model based on multimodal learning represents a significant advancement in educational methodology [9]. Multimodal learning integrates various sensory modalities, such as visual, auditory, and kinesthetic, to enhance the learning experience.…”

Section: Introductionmentioning

confidence: 99%

Design and Application of English-Chinese Bilingual Teaching Model Based on Multimodal Learning

Zhang

2024

jes

View full text Add to dashboard Cite

In the globalized landscape of education, the demand for effective bilingual teaching models has become increasingly prominent, particularly in English and Chinese instruction. this study introduces the Bilingual Teaching Random Conditional Field (BTRCF) as a novel approach to designing and implementing an English-Chinese Bilingual Teaching Model based on Multimodal Learning. The principles of multimodal learning, which integrates various modes of communication such as visual, auditory, and kinaesthetic, the BTRCF model aims to provide students with a comprehensive and immersive language learning experience. The BTRCF model capitalizes on the complementary strengths of both English and Chinese languages, aiming to cultivate bilingual proficiency while fostering cross-cultural understanding among students. By incorporating elements from each language and leveraging multimodal learning strategies, the BTRCF model provides students with a comprehensive language learning experience that extends beyond mere linguistic proficiency to encompass cultural appreciation and intercultural competence. By capitalizing on the complementary strengths of both languages, this model seeks to foster bilingual proficiency while promoting cross-cultural understanding among students. with the BTRCF model have shown promising results, with an average increase of 25% in students' bilingual proficiency scores compared to traditional teaching methods. Additionally, qualitative assessments reveal high levels of student engagement and satisfaction with the multimodal learning approach employed by the BTRCF model, indicating its potential to revolutionize bilingual education practices.

show abstract

Section: Introductionmentioning

confidence: 99%

Design and Application of English-Chinese Bilingual Teaching Model Based on Multimodal Learning

Zhang

2024

jes

View full text Add to dashboard Cite

show abstract

“…As the RNN model has reached its performance bottleneck, the new self-attention mechanism [2] becomes the favorite choice for the translation system design. Machine translation models based on multilayer self-attention (dubbed Transformer) have demonstrated improved translation quality on various large-scale challenges in recent years [7][8][9][10]. For instance, the BERT translation engine [11] has a variable number of encoder layers and self-attention heads.…”

Section: Introductionmentioning

confidence: 99%

Machine Translation of English Language Using the Complexity-Reduced Transformer Model

2022

Mobile Information Systems

View full text Add to dashboard Cite

Previous translation models like statistical machine translation (SMT), rule-based machine translation (RBMT), hybrid machine translation (HMT), and neural machine translation (NMT) have reached their performance bottleneck. The new Transformer-based machine translation model has become the favorite choice for English language translation. For instance, Google’s BERT translation model organizes the Transformer module into bidirectional encoder representations. It is aware of the users’ search intentions as well as the material that the search engine has indexed. It does not need to evaluate previous searches to comprehend what people mean, unlike RankBrain. BERT comprehends words, sentences, and complete information in the same way that we do. It achieves remarkable translation quality improvement over the other state-of-the-art benchmarks. It demonstrates the great potential of the Transformer model. The Transformer-based translation model mainly improves the performance at the cost of growing model sizes and complexity, usually requiring million-scale parameters. It is hard for the traditional computing systems to cope with the growing memory and computation requirements. However, the latest computers can easily run this model without any lag. The biggest challenge of applying the Transformer model is to deploy these models efficiently onto real-time or embedded devices. In this work, we propose a quantization scheme to reduce the parameter and computation complexity. It is of great importance to promote the usage of the Transformer model. Our experiment results show that the original Transformer model in 32 bit floating-point can be quantized to only 8 bits to 12 bits with only negligible translation quality loss. However, due to the perfect transformation of the block part, this quality loss part can easily be managed by the users. Meanwhile, our algorithm achieves 2.6 × to 4.0 × compression ratio, which is helpful to save the required complexity and energy during the inference phase.

show abstract

“…The attention mechanism (AM) was used in machine translation and achieved good results. Subsequently, it was found that introducing attention mechanisms into various neural network fields has a good training effect(Yonglan & Wenjia, 2022;Liu & Guo, 2019).Artificial Intelligence (AI) is based on deep learning, including many neural networks, so the attention mechanism has a good training effect in the field of Artificial Intelligence, attention mechanism has become an important part of neural networks. It has been widely used in the fields of face recognition, natural language processing, and audio processing.…”

mentioning

confidence: 99%

Application of English translation system design based on semantic relation classification in teaching ecological health

Xie

2023

Preprint

View full text Add to dashboard Cite

At present, the teaching ecology in the public environment is not healthy. The relationship between the ecological subjects (teachers and students) is indifferent and lacks resonance. Students' resistance to teaching leads to ineffective teaching. Meanwhile, the accuracy of English machine translation is generally not high, and there are problems such as insufficient accuracy of the semantic classification and unclear semantic expression. To improve the model robustness and solve the semantic classification problem in the NMT task, this paper proposes a lightweight bidirectional LSTM network SAT-BiLSTM (Bi-directional Long Short-Term Memory) with an attention mechanism. The SAT-BiLSTM translation network is composed of six decoders and six encoders, and the bidirectional LSTM network with an improved strong attention mechanism is used to process the input text and the output text. Experimental results show that compared with other NMT models, the system improves the translation speed and accuracy, achieves better statistical results on rare words translation, and the semantic classification is more accurate. This study is helpful to improve the effectiveness of English classroom teaching and create a healthy college English classroom ecosystem.

show abstract

English-Chinese Machine Translation Model Based on Bidirectional Neural Network with Attention Mechanism

Cited by 12 publications

References 29 publications

Design and Application of English-Chinese Bilingual Teaching Model Based on Multimodal Learning

Design and Application of English-Chinese Bilingual Teaching Model Based on Multimodal Learning

Machine Translation of English Language Using the Complexity-Reduced Transformer Model

Application of English translation system design based on semantic relation classification in teaching ecological health

Contact Info

Product

Resources

About