Research on English Language Models in Multimodal Machine Translation for Unstructured Data

This paper proposes a multi-modal machine translation method for unstructured data based on deep learning. Firstly, a training dataset containing large-scale English-Chinese bilingual parallel sentence pairs and monolingual corpus is constructed to train the multimodal encoder-decoder framework. Secondly, a computer intelligent proofreading system for English translation is designed to provide real-time feedback through the human-computer interface to further optimize the translation results and ensure the fluency and accuracy of the translated text. Finally, the translation results are displayed through the human-computer interface, and the computer intelligent proofreading function is provided to further improve the translation quality. The experimental results show that the proposed method achieves good translation results on multiple test sets, which proves its advantage in processing unstructured data. The research in this paper provides a new idea and method for the development of multimodal machine translation, which is helpful to promote the application and development of artificial intelligence technology in the field of language service.