A machine translation method

Abstract

The invention discloses a machine translation method and belongs to the technical field of natural language processing. The method of the present invention is: 1) converting the bilingual sentence of word alignment into a bilingual syntax tree structure; 2) extracting phrases with structural attributes at each layer of the bilingual syntax tree, and calculating the phrase translation probability to form a phrase translation table; 3) According to the phrase translation table, use the search algorithm to translate the bilingual sentences to be translated; among them, the tree nodes of the bilingual syntax tree are bilingual word pairs or bilingual phrase pairs that are mutually translated, and the source language end of the parent node of the syntax tree is owned by the parent node The order-preserving combination of the source language end of the child node is obtained, and the target language end is obtained by combining the target language ends of all the son nodes of the parent node in the set word combination order, and the combination of the nodes in the adjacent upper and lower layers in the syntax tree at the target language end The order is reversed; the combination order includes order preservation or reverse order. The invention achieves the effect of improving the translation quality by improving the internal structure of the translation candidate.

Description

technical field [0001] The invention belongs to the technical field of natural language processing, in particular, the invention relates to a machine translation method. Background technique [0002] The analysis of sentence structure in statistical machine translation methods can improve the quality of translations. At present, there are two main methods for sentence structure analysis, one is the linguistic syntax method that uses a syntax analyzer that conforms to the linguistic meaning to analyze the sentence structure (refer to K.Yamada and K.Knight.2001.A Syntax- based Statistical Translation Model.in Proceedings of ACL.p.523-530. and Y.Liu, Q.Liu, and S.Lin.2006.Tree-to-String AlignmentTemplate for Statistical Machine Translation.in Proceedings of ACL.p.609 -616.), the other is a formalized syntax method that does not require a clear syntax analysis process (refer to D. Wu, Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora. Computat...

AI Technical Summary

Problems solved by technology

The method based on hierarchical phrases extracts phrases with intervals from word-aligned bilingual sentences, and uses the expansion of intervals to obtain a hierarchical syntactic analysis tree. In the process of sentence structure generation, this method only considers the input The information of the source language sentence does not consider the impact of the target language on translation

The method based on reverse transcription grammar allows two forms of word position exchange (preservation and reverse order), and the number of words in each exchange is limited to two. Therefore, the generated sentence structure is expressed in the form of a binary tree. The shortcoming of the method is that the position exchange of words is limited to only between two nodes, and there may be too many useless exchange structures in actual translation, which leads to the problem of high translation error rate

Images