A Study on Lexical Disambiguation in English Translation Based on Twin Neural Networks

Abstract

To solve the problem of the lack of effective algorithmic models to improve the accuracy of lexical disambiguation in English translation, this paper constructs a twin network lexical disambiguation model based on the characteristics of twin networks, and studies the construction process from the original corpus to the input sample pairs. The Stacked-LSTM algorithm is utilized to align the input Chinese and English corpus and expand the dataset. To achieve disambiguation, the input sample similarity is calculated after training the twin neural network, which extracts corpus features using BiLSTM Attention. After comparing the disambiguation experiments of various algorithms, the model of this algorithm can effectively calculate the similarity of the input samples and achieve the disambiguation accuracy of 68.23% for English vocabulary translation, and 87.0% for vocabulary segmentation of complex English sentences or articles. This shows that the model of this algorithm has good performance for disambiguating English translations.