Research on error detection in English translation texts using machine learning algorithms

Abstract

This paper provides a concise overview of a grammatical error correction algorithm based on the encoder-decoder structure. The traditional unidirectional long short-term memory (LSTM) in the encoder was transformed into a bidirectional LSTM. Subsequently, the grammatical error correction algorithm was simulated and experimented with. In the experiments, it was compared with two other error correction algorithms: one based on the LSTM classification model and the other on the traditional unidirectional LSTM translation model. The results indicated that the three error correction algorithms exhibited little difference in detection performance when faced with distinct corpus databases. Furthermore, when dealing with the same corpus database, the bidirectional LSTM algorithm demonstrated the most robust detection performance, followed by the one based on the traditional unidirectional LSTM translation model, and lastly, the one based on the LSTM classification model performed the least effectively.