Title: An English translation syntax error recognition based on improved transformer model

Authors: Wenjuan Che

Addresses: College of Humanities, Gansu Agricultural University, Lanzhou, Gansu Province, China

Abstract: In order to overcome the problems of low recognition rate, high-error rate and long processing time of traditional English translation syntax error recognition methods, an English translation syntax error recognition method based on improved transformer model is proposed. The Kneser-Ney method is used to smoothy process the English translation text, and the Hidden Markov model is used to label the smoothed English translation sequence to extract the character features, part of speech features and part of speech features of the English translation sequence. The transformer model is improved through the global location of entities, and the improved transformer model and syntax error feature tags are used to recognition syntax error in English translation. The experimental results show that the maximum recognition rate of method of this paper is 97.1%, the minimum error recognition rate is 3.2% and the average processing time is 0.72 s.

Keywords: improved transformer model; English translation; syntax error recognition; smooth processing; Hidden Markov model; feature tags.

DOI: 10.1504/IJCAT.2023.138830

International Journal of Computer Applications in Technology, 2023 Vol.73 No.4, pp.261 - 270

Received: 21 Sep 2023
Accepted: 15 Dec 2023
Published online: 31 May 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article