Translation machine testing method based on syntax tree pruning

Abstract

The invention relates to a machine translation test method. According to the method, a dependency syntax tree is constructed for sentences, pruning is performed on the syntax tree according to a specific rule, validity of the sentences is destroyed based on a group of deletion operators of a dependency syntax tree level, and words or phrases are deleted from the original sentences to generate new sentences with effective grammar and semantics. And inputting the original text and the newly generated sentences into a tested machine translation system, calculating bag-of-word distances, sequencing and amplifying the sentences according to the bag-of-word distances, selecting five sentences with the largest distance, manually labeling the original sentence and the translated sentence results, marking wrong sentences, and completing the test of the machine translation system. The invention aims to solve the problem that the test performance is mainly limited by the maturity of an adopted language model due to the fact that a test case is mainly generated by replacing a part of words in a sentence in the current machine translation test. When the data is amplified, the invariance of the basic structure of the sentence is ensured, so that more pairs of errors are found, and most of the errors cannot be found by a previous machine translation test technology.

Description

technical field [0001] The invention belongs to the field of machine translation in information technology, and is particularly suitable for machine translation testing in machine translation. The purpose of the invention is to generate test sentences in machine translation testing, and it is a translation machine testing method capable of generating a large number of test sentences. Background technique [0002] Machine translation is the task of using computers to convert one natural language into another natural language, and it is one of the hot issues in the field of artificial intelligence research. In recent years, with the development of deep learning, neural machine translation models based on sequence-to-sequence structures have achieved better results than statistical machine translation models in translation tasks of multiple language pairs, and have been widely used in commercial translation systems. Although the actual application effect of the commercial trans...

AI Technical Summary

Problems solved by technology

[0006] The present invention solves the existing problem of difficult translation machine testing by proposing a translation machine testing method based on grammar tree pruning, and then helps the machine translation system to improve the quality of translation and reduce the possibility of translation errors, thereby providing the public with more good translation quality

Images