A Comparative Study of Text Genres in English-Chinese Translation Effects Based on Deep Learning LSTM

Abstract

In recent years, neural network-based English-Chinese translation models have gradually supplanted traditional translation methods. The neural translation model primarily models the entire translation process using the “encoder-attention-decoder” structure. Simultaneously, grammar knowledge is essential for translation, as it aids in the grammatical representation of word sequences and reduces grammatical errors. The focus of this article is on two major studies on attention mechanisms and grammatical knowledge, which will be used to carry out the following two studies. Firstly, in view of the existing neural network structure to build translation model caused by long distance dependent on long-distance information lost in the delivery, leading to problems in terms of the translation effect which is not ideal, put forward a kind of embedded attention long short-term memory (LSTM) network translation model. Secondly, in view of the lack of grammatical prior knowledge in translation models, a method is proposed to integrate grammatical information into translation models as prior knowledge. Finally, the proposed model is simulated on the IWSLT2019 dataset. The results show that the proposed model has a better representation of source language context information than the existing translation model based on the standard LSTM model.

Corpus-based Research on English-Chinese Translation Teaching Combining Vocabulary Learning and Practice

“…Zhao and Jin [24] have suggested that traditional translation techniques have gradually been replaced by English-Chinese translation models based on neural networks. The "encoder-attention-decoder" The neural translation model's primary tool for simulating the entire translation process is structure.…”

AI-driven Generation of News Summaries Leveraging GPT and Pegasus Summarizer for Efficient Information Extraction

“…The study highlights the importance of considering the relationship between words and categories in the classification of news texts, which is often neglected in previous approaches. English-Chinese translation models based on neural networks have replaced traditional methods, and [16] focuses on attention mechanisms and grammatical knowledge in translation models. It proposes a translation model based on the integration of LSTM attention and the LSTM model combined with prior grammatical knowledge, to improve the representation of source language contextual information and enhance translation quality.…”

“…Whereas the LSTM model combined with prior syntactic knowledge, using simple identifiers to identify target terms as a group, helped the translation model to better integrate terminological knowledge during training and learn the semantic relationship between target terms and source statements. [16] points out that integrating the neural machine translation model can improve the neural machine translation model and enhance translation quality. In [17], abstract summarization of Arabic texts is considered a difficult task due to the complexity of the language.…”