magazinelogo

Engineering Advances

Downloads: 192919 Total View: 1380299
Frequency: quarterly ISSN Online: 2768-7961 CODEN: EANDDL
Email: ea@hillpublisher.com Citations: 135
ArticleOpen Access http://dx.doi.org/10.26855/ea.2025.10.008

Research on Cross-language Intelligent Interaction Integrating NLP and Generative Models

Qizeng Sun

Moyi Tech, Iselin, NJ 08830, USA.

*Corresponding author: Qizeng Sun

Published: November 18,2025

Abstract

A study was conducted on cross-lingual intelligent interaction integrating natural language processing (NLP) and generative models. The research aimed to clarify the core requirements of cross-lingual communication and to explore the role of technical integration in improving the naturalness and accuracy of interaction. The methodology combined a literature review with typical application analysis, focusing on semantic parsing, generation control, and scenario practice. The results indicate that interaction patterns based on the integration pathway effectively address semantic alignment and contextual consistency issues in cross-lingual dialogue, significantly enhancing the fluency of expression and adaptability to multiple languages. The conclusion highlights that this approach possesses strong scalability and provides valuable reference for cross-lingual applications in educational platforms, international customer service, and public services.

Keywords

Cross-lingual intelligent interaction; Natural language processing; Generative model; Semantic alignment; Application outcome

References

[1] Zhang J, Iglesias ÁC. Special Issue on Recent Applications of Machine Learning in Natural Language Processing (NLP). Appl Sci. 2025;15(11):6110.

[2] Xie J, Deng S, Hou X, Zhang Y, Li M, Wang L, et al. CLIMS++: Cross Language Image Matching with Automatic Context Discovery for Weakly Supervised Semantic Segmentation. Int J Comput Vis. 2025;133(8):1-20.

[3] Niu X, Bai B, Guo N, Niu K, Wang Z. Rate-Distortion-Perception Trade-Off in Information Theory, Generative Models, and Intelligent Communications. Entropy (Basel). 2025;27(4):373.

[4] Nath U, Singh R, Shukla A, Ghosh S, Maji S. Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models. Int J Comput Vis. 2024;133(5):1-29.

[5] Wang Z, Ezukwoke K, Hoayek A, Xie X, Bordatchev E. Correction: Natural language processing (NLP) and association rules (AR)-based knowledge extraction for intelligent fault analysis: a case study in semiconductor industry. J Intell Manuf. 2023;36(1):1.

[6] Li R, Wang S. The Application of Human-Machine Intelligent Interaction Technology in the Practice of Foreign Language Intelligent Education. Int J New Dev Educ. 2023;5(25).

[7] Rui L, Cheng L, Dazhi J. Efficient dynamic feature adaptation for cross language sentiment analysis with biased adversarial training. Knowl Based Syst. 2023;279.

[8] Shruthi J, Suma S, Sarika C. Survey on - Socially Intelligent Robots by using NLP. Int J Comput Appl. 2017;171(1):19-21.

How to cite this paper

Research on Cross-language Intelligent Interaction Integrating NLP and Generative Models

How to cite this paper: Qizeng Sun. (2025). Research on Cross-language Intelligent Interaction Integrating NLP and Generative Models. Engineering Advances5(4), 172-176.

DOI: http://dx.doi.org/10.26855/ea.2025.10.008