An English word and case joint prediction method based on neural machine translation

Abstract

The invention discloses an English word and case joint prediction method thereof based on neural machine translation, which mainly comprises the following steps of: establishing a training data set and making a vocabulary; converting the training data set into a vector training set according to the vocabulary; training the translation model, adding the predicted word loss and the predicted word case loss as the total predicted loss of the translation model; when the total loss is no longer reduced in the training process, stopping training of the model; translating Chinese using a trained translation model; after the completion of translation, according to the English translation and the corresponding word case attribute information, restoring the word in the translation to its due form, and obtaining the official translation. The method of the invention not only reduces the size of the vocabulary and the model parameters, but also improves the quality of the translation.

Description

technical field [0001] The invention relates to a machine translation method, in particular to a method for predicting the case of Chinese and English words from Chinese to English Background technique [0002] Driven by practical applications, machine translation has been a research hotspot that has attracted much attention in recent years. The mainstream solution before machine translation is statistical machine translation. In recent years, deep learning and neural networks have been well developed in the field of images, and have achieved results beyond humans in the field of classification. The neural network method is also rapidly being widely used in other fields. In 2014, Jacob Devlin proposed a neural network joint model, which has achieved significant improvements compared to traditional statistical machine translation methods. This year, Microsoft Hany and others applied neural machine translation, surpassing the quality of translation for the first time. [0...

AI Technical Summary

Problems solved by technology

The above methods are all carried out on a single corpus. After the translation is completed, the upper and lower case of the target translation is restored, which increases the processing steps and time overhead.

And these methods do not consider the situation of the source corpus, when the translation result is inaccurate, it will greatly interfere with the recovery of word case information

Images