Method for extracting phrases of statistical machine translation

Abstract

The invention provides a method for extracting phrases of statistical machine translation, which comprises the following steps of: 1) acquiring a plurality of aligned sentence pair combinations from a bilingual language material from two directions, and calculating the priori probability of the plurality of aligned sentence pair combinations; 2) calculating the alignment probability of word pairsaccording to the sum of the priori probabilities of the word pairs of the plurality of aligned sentence pair combinations, and forming an alignment matrix by using the alignment probability of the word pairs; 3) calculating the frequency of phrase alignment according to the alignment matrix; and 4) calculating the relative frequency and the lexicalization probability of the phrase alignment according to the frequency of the phrase alignment. The method can effectively express all probable aligned phrase combinations, and improves the quality of phrase extraction, thereby being capable of improving the quality of translation which is performed according to the extracted phrases.

Description

technical field [0001] The present invention relates to the field of natural language processing, and more particularly, to the field of statistical machine translation of texts. Background technique [0002] With the rapid development of the world economy, cultural and economic exchanges between countries are becoming more and more frequent. People sometimes have to face materials and information in various languages ​​from various countries in their daily work and life. A major problem is that of language comprehension, where people need to be able to comprehend material written in a language other than their own in a relatively short period of time. [0003] Therefore, machine translation technology came into being. Early machine translation mainly focused on the research of rule translation systems, but the writing of translation rules required the participation of language experts, and usually a large number of rules had to be rewritten every time a translation field wa...

AI Technical Summary

Problems solved by technology

Due to the limitation of the size and quality of the bilingual corpus, the alignment quality represented by the alignment matrix is ​​not ideal, resulting in poor phrase tables extracted, further resulting in poor translation quality

Images