Translation method and device

Abstract

The embodiment of the invention discloses a translation method and device. The method adopts a translation model, the translation model comprises an encoder, a classifier and a decoder, and the methodcomprises the following steps: inputting a vector matrix determined based on a word segmentation sequence of a first text into the encoder to obtain an intermediate representation output by the encoder; inputting the intermediate representation into a classifier to obtain a classification label output by the classifier; and in response to the fact that the classification tag indicates that the segmented word located at the tail in the segmented word sequence of the first text is an independent translation unit, inputting the intermediate representation into a decoder to obtain a second text output by the decoder. According to the method, the system time consumption is reduced under the condition that the translation quality is guaranteed, improvement is easy to carry out on the basis of an existing translation model, use is easy, and supervised learning is introduced to achieve control over the translation unit.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular to the field of translation technology, and in particular to a translation method and device. Background technique [0002] Simultaneous interpretation has developed rapidly in the past two years, and major Internet companies have launched their own simultaneous interpretation products one after another. [0003] Most of the current simultaneous interpretation systems are based on the pipeline (pipeline). First, the text is generated through speech recognition (ASR), and then the sentence segmentation module is called to segment the text, and then the translation model is called to translate the text after the sentence segmentation, and finally the translation result is displayed. . Specifically, the simultaneous interpretation system increases the frequency of sentence segmentation and reduces the granularity of sentence segmentation. Or, the simultaneous interpretatio...

AI Technical Summary

Problems solved by technology

[0004] However, if the simultaneous interpretation system increases the frequency of calling translation by frequently adding punctuation, it will increase the probability of wrong sentence segmentation, which will affect the quality of translation, and if there is semantic dependence between clauses, it will further increase translation errors; The translation delay is still large

If the simultaneous interpretation system adopts the wait-k words model, it will greatly help reduce the delay of the simultaneous interpretation system, but it still needs to rely on an additional sentence segmentation module, otherwise the translation result will be delayed more and more than the recognition result In the case of Chinese-English translation, under the same meaning, the average English sentence length is about 1.25 times that of Chinese (Huang and Zhao, When to finish? Optimal beam search for neural text generation), if there is no "catch-up" at the moment of sentence breaking, English will forever behind Chinese

In addition, the wait-k model requires that a word must be decoded at each moment. When the recognition result information is insufficient, the decoded word is likely to be wrong, which will affect the translation effect.

Images