Multi-language intelligent preprocessing real-time statistical machine translation system

Abstract

The invention discloses a multi-language intelligent preprocessing real-time statistical machine translation system. The multi-language intelligent preprocessing real-time statistical machine translation system comprises a receiving module, a preprocessing module, a machine translation module and a postprocessing module, wherein the receiving module comprises a text language receiving module and a voice recognition result receiving module; the preprocessing module comprises a text preprocessing module and a voice recognition result preprocessing module; the machine translation module is used for learning phrase-to-phrase translation, finding out corresponding translated phrases through phrases processed by the preprocessing module and connecting the phrases to form an integrated sentence; and the postprocessing module is used for performing word punctuation normalized processing, capital and small letter normalized processing and format normalized processing on the translation result, enabling the translation result to be close to the expression habit of the target language and finally outputting the result. The multi-language intelligent preprocessing real-time statistical machine translation system can be used for translating text language and voice language and improves the translation accuracy on small-probability words and phrases.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence machine translation, in particular to a multilingual intelligent preprocessing real-time statistical machine translation system. Background technique [0002] Machine translation is a technology that uses computers to automatically translate human natural languages. It is a process that uses computers to convert one natural language into another natural language, and the two natural languages ​​should be equivalent in meaning. [0003] At present, a relatively mature and mainstream machine translation method is based on statistics. The advantage of this method is that it hardly requires manual translation rules, and all translation information is automatically learned from the corpus. Therefore, this method is the most To the greatest extent, the characteristics of high-speed computing of the computer are played, and the labor cost is greatly reduced. [0004] Machine tran...

AI Technical Summary

Problems solved by technology

[0005] However, this kind of machine translation based on co-occurrence frequency and probabilistic method is not capable of processing low-probability phrases (such as translation of proper nouns). In addition, how to add grammatical and semantic expressions to the statistical model so that the generated translated sentences are more in line with People's expression habits are also a problem that machine translation technology needs to solve

Images