Word-by-word comparison method for realizing high hit rate

Abstract

A method for a word for word comparison between Chinese and English. The method comprises the following steps: 1) forming an English data string by a plurality of English data string units, and forming a Chinese data string by a plurality of Chinese data string units; 2) segmenting the English data string to obtain a result set of segmented English phrases of phrase length; 3) determining whether or not an item in the result set of the segmented English phrases exists in a list of keyword characters; if the determination is negative, stopping; if the determination is positive, proceeding to step 4); 4) searching an English-Chinese dictionary to obtain a corresponding Chinese ID sequence; 5) determining whether or not the same exists in the list of keyword characters; if the determination is positive, proceeding to step 6); 6) searching the Chinese ID sequence for a related Chinese word sequence; 7) determining whether or not the related Chinese word sequence exists in the list of keyword characters; if the determination is positive, proceeding to step 8); 8) performing data string matching on the related Chinese word sequence in the Chinese data string, and then proceeding to step 9) if there is a match; 9) adding a mark to the English and the Chinese to indicate a hit, and deleting the related Chinese word sequence from the Chinese data string. The present invention achieves a word for word comparison with a high hit rate by solving a critical domain problem in comparison.

Description

technical field [0001] The invention relates to a Chinese-English word-by-word comparison method, which realizes a word-by-word comparison with a high hit rate by solving the key field problem in the comparison. Background technique [0002] In the process of daily English learning, we often encounter the situation of comparing Chinese and English. It would be very pleasant if we could provide a simple word-by-word comparison method. After the current Chinese-to-English markup is used, there are misses caused by too thick Chinese word segmentation. For example, there is a word "I think" in Chinese, but there is no "I think" in its English relationship. It leads to word segmentation results, but cannot be marked. In our common Chinese-English sentence examples, there are often verbs, articles or prepositions that cannot be translated into meaningless words in the corresponding language example sentences. When comparing word by word, it is necessary to correspond to Chinese a...

AI Technical Summary

Problems solved by technology

After the current Chinese-to-English markup is used, there are misses caused by the Chinese participle being too thick. For example, there is a participle "I think" in Chinese, but there is no "I think" in its English relationship.

Cause word segmentation results, but cannot be marked

In our common Chinese-English sentence examples, there are often verbs, articles or prepositions that cannot be translated into meaningless words in the corresponding language example sentences. When comparing word by word, it is necessary to correspond to Chinese and English Tags, such words cannot be added to the tag sequence due to their meaninglessness

In the process of successive comparison between Chinese and English, there will be a situation where one Chinese corresponds to multiple English. The usual practice is to mark them in order, which will lead to the wrong position of the mark when the English example sentence is an inverted sentence.

In the word-by-word comparison function, it is necessary to mark the Chinese and the corresponding English at the same time. However, since most of the collected data comes from dictionary data, it is largely a standard interpretation, but the actual Chinese-English example sentences are not. There are various flexible applications, resulting in frequent cases where the corresponding data cannot be found according to the standard interpretation

Images