Neural machine translation method based on translation memory bank

Abstract

The invention discloses a neural machine translation method based on a translation memory bank. The method comprises the following steps: crawling massive bilingual data from a network containing foreign language data; preprocessing the bilingual data to obtain processed bilingual data; storing half of the bilingual data as basic data of a translation memory bank, and adopting the other half of the bilingual data to find sentences most similar to each sentence in the training corpus in the translation memory bank by using a search technology; inputting the training corpus data and the translation memory bank data into the neural network model together to start training the model; importing user-defined data into a translation memory bank; searching a text input by a user in real time to find a sentence most similar to the text in a translation memory bank, inputting the sentence into a machine translation model, and guiding model translation at a decoding end by using a gating mechanism; and storing the sentence input by the user and the revised result into a translation memory bank. The advanced neural machine translation technology is applied, the translation effect is excellent, and the high-quality requirements of different users for translated texts are met.

Description

Technical field [0001] The present invention relates to a neurometric translation method, specifically based on a meta-mechanical translation method based on a translation memory. Background technique [0002] Machine translation is the process of converting a natural language into another natural language using a computer. With the rapid development of the Internet, machine translation has played an increasingly important role in various aspects of economic, cultural exchanges, and politics, which also reflects the practical value of machine translation. The biggest advantage of machine translation is fast, just enter a piece of text, you can see the result. Nowadays, many software have also achieved translation of the whole text and the entire article, which is unmatched by manpower. [0003] Neural Machine Translation (NMT) is a depth study-based machine translation method, which provides the most advanced translation performance in the case of massive parallel text. Neural ma...

AI Technical Summary

Problems solved by technology

It is important to note that a normal translation memory system will only search the source language from its database, text segments with no similarities at all will have to be translated manually by the translator, and these newly translated text segments will be stored in the database , future translations may be immediately adopted due to the repetition of the source text

Images