Method of translation, method for determining target information and related devices

Abstract

The invention discloses a method for determining target information. The method includes the following steps that encoding is conducted on to-be-processed text information to obtain a source-end vector expression sequence; according to the source-end vector expression sequence, a source-end context vector corresponding to the first moment is obtained, wherein the source-end context vector is used for expressing to-be-processed source-end content; according to the source-end vector expression sequence and the source-end context vector, a first translation vector and / or a second translation vector are / is determined, wherein the first translation vector indicates the source-end content which is not translated in the source-end vector expression sequence within the first moment, and the second translation vector indicates the source-end content which is translated in the source-end vector expression sequence within the second moment; decoding is conducted on the first translation vector and / or a second translation vector and the source-end context vector so as to obtain the target information of the first moment. The invention further provides a method of translation and a device for determining the target information. According to the method for determining the target information, the model training difficulty of a decoder can be reduced, and the translation effect of a translation system is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a translation method, a method for determining target information and related devices. Background technique [0002] Machine translation (MT) refers to the process of using machines to convert text or speech from one language to another language with the same meaning. With the rise of deep learning, deep neural network technology has also been applied to MT in the past two years, and neural machine translation (NMT) has become a new generation of translation technology. [0003] At present, NMT uses the encoder-decoder framework to implement the process of understanding semantics and re-translation. This process mainly includes the encoder generating the source-end vector representation at the current moment, and then the decoder uses the source-end vector representation and the source-end context at the current moment. Output the decoder state at the current moment, and final...

AI Technical Summary

Problems solved by technology

[0004] However, in the existing scheme, the decoder needs to build a language model, record the information that has been translated in the past, and record the information that needs to be translated in the future. These operations will increase the difficulty of the model training of the decoder and reduce the accuracy of the model training. Cases of duplicate translations and missing translations

Images