Dependency coherence constraint-based automatic alignment method for bilingual words

Abstract

The invention discloses a dependency coherence constraint-based automatic alignment method for bilingual words. The method comprises the following steps of: performing dependency parsing on a training sentence pair; in a training stage, training a word alignment model based on a dependency coherence constraint between a source language end and a target language end by utilizing the training sentence pair and a dependency syntax tree; and in a test stage, generating word alignment results in line with the dependency coherence constraint between the source language end and the target language end for a test sentence pair by utilizing the word alignment model based on the dependency coherence constraint between the source language end and the target language end, and combining the two word alignment results to generate a word alignment result in line with a bilingual dependency coherence constraint, wherein the word alignment result combines accuracy and a recalling rate. Compared with the prior art, the method is low in word alignment error rate.

Description

technical field [0001] The invention belongs to the field of natural language processing, in particular to statistical machine translation and methods for automatic alignment of bilingual words. Background technique [0002] Word alignment, as the name suggests, is to identify the translation correspondence between the translated sentences in two languages ​​in units of words. Word alignment is an important part of statistical machine translation. It is the basis for extracting phrase tables and ordering rules in phrase-based translation models, and even the basis for extracting syntactic translation rules in syntax-based translation models. Usually, the quality of word alignment directly affects the translation quality of statistical machine translation systems. [0003] Word alignment methods can be roughly divided into two categories: heuristic methods and statistical methods. The heuristic method judges whether words are aligned by calculating the co-occurrence measure...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is that the generative word alignment model does not incorporate syntactic information and the training of the discriminative word alignment model requires manually labeled word alignment corpus

Images