Machine translation model training method and device and electronic equipment

Abstract

The embodiment of the invention provides a machine translation model training method and device and electronic equipment. The machine translation model training method comprises the steps: employing afirst parallel corpus, and carrying out preliminary training on a translation model from a target end to a source end; utilizing the trained translation model from the target end to the source end totranslate each sentence in a definite monolingual corpus to obtain a synthetic corpus, and splicing the synthetic corpus with the definite monolingual corpus to obtain a second parallel corpus; evaluating the credibility of a translation result obtained by using the trained translation model from the target end to the source end by using a Monte-Carlo random inactivation algorithm; and based on the credibility, training a translation model from a source end to a target end by utilizing an integral corpus formed by the first parallel corpus and the second parallel corpus. According to the embodiment of the invention, the translation model can still be accurately trained in the presence of noise interference, and the accuracy of the translation model is ensured.

Description

technical field [0001] The present invention relates to the technical field of machine translation, and more specifically, to a training method, device and electronic equipment for a machine translation model. Background technique [0002] In the field of language translation, in order to realize automatic machine translation, the current technology usually adopts a method based on neural network, which needs to collect large-scale high-quality parallel corpus to train a reliable neural network model. However, high-quality parallel corpora often only exist among a small number of languages, and are often limited to certain specific fields, such as government documents, news, etc. [0003] At present, with the development of key technologies such as databases and the Internet, electronic documents in various languages ​​and fields are increasingly abundant, providing rich monolingual corpus for machine translation, which also provides great convenience for solving the above p...

AI Technical Summary

Problems solved by technology

[0005] However, a large parallel corpus cannot eliminate possible errors in machine translation itself. When errors occur in machine translation itself, the translation results obtained will be noisy, which will affect the accuracy of the translation results and fail to achieve the desired effect.

Images