English text concept understanding method

Abstract

The invention discloses an English text concept understanding method. The method is an understanding model composed of an English text understanding preprocessing module, an English text keyword concept semantic feature extraction module, an English text keyword and concept semantic dependency relationship extraction module and a candidate answer selection module which are connected in sequence. After an English text and questions related to the English text are processed by the understanding method, related concept answers of the questions can be finally obtained. According to the method of the invention, the problem of English text concept understanding is solved, and the answer result is more accurate than that of a traditional English text understanding method.

Description

technical field [0001] The invention relates to natural language processing technology, and is an English text concept understanding method. The understanding method of the invention is only suitable for English texts, not Chinese texts. Background technique [0002] Machine-automated English text understanding is to input a piece of English text and several questions related to the text, and the machine relies on its own algorithm to find the answer to the question from the input English text. The traditional English text understanding methods mainly include text-question semantic analysis and understanding method and text-question vocabulary matching comprehension method. The text-question semantic analysis and understanding method mainly relies on pre-defined rule templates, and uses hand-designed language features to learn the relationship between text and questions. This method first requires a large amount of manually labeled data, which will cause semantic features. ...

AI Technical Summary

Problems solved by technology

The text-question semantic analysis and understanding method mainly relies on pre-defined rule templates, and uses hand-designed language features to learn the relationship between text and questions. This method first requires a large amount of manually labeled data, which will cause semantic features. sparse problems, and this method is only suitable for certain limited domains

The text-question vocabulary matching comprehension method calculates the semantic similarity between the key words in the text and the question, so as to select a word or phrase with a high similarity as the answer. This method only matches the similarity between the words in the question and the English text information, it is difficult to obtain the accurate semantics of polysemous words in English texts, which leads to the problem of inaccurate answer selection in reading comprehension

Images