Model training method and device and translation method and device

Abstract

The invention relates to the field of artificial intelligence, and discloses a model training method and device and a translation method and device. The model training method comprises the steps: using a first monolingual corpus to train a model to obtain a first PLM, and using a second monolingual corpus to train the model to obtain a second PLM; obtaining word vector parameters of the first translation model based on the first PLM; and training the first translation model by using the high-resource parallel corpus to obtain a trained first translation model, obtaining a second translation model according to the trained first translation model and the second PLM, and training the second translation model by using the low-resource parallel corpus to obtain a trained second translation model. According to the scheme provided by the invention, in a model training stage, the high-resource parallel corpus, the low-resource parallel corpus, the first monolingual corpus and the second monolingual corpus are utilized at the same time, so that the trained model also has a good translation effect in a low-resource scene.

Description

Technical field [0001] The present application relates to the field of artificial intelligence, and in particular, a method of model training, a method of translation, and a device. Background technique [0002] Artificial Intelligence (AI) is the use of digital computer or digital computer-controlled machine simulation, extension, and extension of people's intelligence, perceived environments, access to knowledge, and use knowledge to achieve best results, methods, techniques, and application systems. In other words, artificial intelligence is a branch of computer science. It is attempt to understand the essence of intelligence and produce a new intelligent machine that can react in a manner similar way. Artificial intelligence is to study the design principles and implementation methods of a variety of intelligent machines, making machines with perception, reasoning and decision-making. [0003] With the development of AI technology, Neural Machine Translation, NMT models are w...

AI Technical Summary

Problems solved by technology

In low-resource scenarios, the translation effect of NMT models tends to decline significantly. Therefore, it is urgent to improve the translation effect of NMT models in low-resource scenarios.

Images