Text translation processing method and device

Abstract

The embodiment of the invention provides a text translation processing method and device, and belongs to the technical field of language processing. The method comprises the steps of if the recognition credibility of a first recognition text is larger than a first preset threshold value and the translation credibility of a first target language text is not larger than a second preset threshold value, translating the first target language text to obtain a second recognition text; if the semantics between the first recognition text and the second recognition text is not equivalent, obtaining a key noun and the type of the key noun; based on the type of the key noun, translating the key noun to obtain a first translation result, translating other contents except the key noun in the first recognition text to obtain a second translation result and merging the first translation result and the second translation result to obtain a second target language text. Since the key noun in the first recognition text can be used as an overall split word, according to the keyword type, the type of the key noun is translated, and thus the translation result can be more accurate.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of language processing, and more specifically, relate to a text translation processing method and device. Background technique [0002] Language communication has become an important issue faced by different language and ethnic groups in mutual communication. The traditional language service industry uses manual escort interpretation, consecutive interpretation, and simultaneous interpretation to solve the problem of language communication barriers. However, due to insufficient manpower and cost constraints, it cannot meet the needs of ordinary people for communication in different languages. The development of speech translation technology has made a useful supplement to the traditional language interpretation service industry, providing another way for ordinary people to communicate in daily life, and has more advantages in terms of cost and timeliness. [0003] The speech translatio...

AI Technical Summary

Problems solved by technology

Especially for some names of people, places and institutions, since most of these entity nouns are rare words, they appear in a small proportion in the training corpus of speech recognition and machine translation, or even never appear, so it is easier in the process of recognition and translation An error has affected the effect of voice translation in practical applications

Images