Translation text integrity evaluation method based on bilingual text structure information

Abstract

The invention discloses a translation text integrity evaluation method based on bilingual text structure information. The method includes the following steps of firstly, extracting training corpus used for establishing a target end text unit integrity model from a target end texture structure tree; secondly, establishing the target end text unit integrity model through the training corpus generated in the first step; thirdly, integrating the target end text unit integrity model in a logarithm linear translation model, and conducting translation generation through an adaptability decoding method. According to the method, with the help of the bilingual text structure information, a decoder can further improve the translation quality of the current statistical machine translation by fully and approximately utilizing the semantic integrity information based on bilingual text language knowledge.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to a statistical machine translation method based on discourse analysis. Background technique [0002] Machine translation (machine translation, MT) refers to the translation of a natural language (usually called source language, source language) into another natural language (usually called target language, target language) with the help of computer technology. [0003] After more than 20 years of development, the research on statistical machine translation has achieved a series of innovative results, and both translation models and practical systems are constantly being improved and improved. From word-based translation models to phrase-based translation models, and then to syntax-based translation models, people have gradually integrated linguistic knowledge into statistical machine translation. Currently, machine translation can achieve good results for some ...

AI Technical Summary

Problems solved by technology

However, in the existing machine translation system, because the division of phrases and ordering do not take into account the problem of semantic integrity, the final translation result is only determined according to the scores of translation probability and language model, so the translation often appears Cases where semantic unit integrity is compromised

This not only affects the fluency and coherence of the entire translation, but also misleads readers' understanding of the translation.

Images