Chinese question semantic comprehension method utilizing semantic dependency analysis

Abstract

The invention relates to a Chinese question semantic comprehension method by utilizing semantic dependency analysis, which comprises the following steps of: step 1, collecting and sorting a question data set in an application field; step 2, preprocessing the obtained question data set; step 3, constructing a semantic dependency analysis model based on BiLSTM (Bidirectional Long Short Term Memory); step 4, constructing a semantic dependency structure analysis rule; and step 5, mapping the query triad list obtained by conversion in the step 4 into a basic diagram mode in the SPARQL statement to form a triad mode relationship. According to the method, through the semantic dependency analysis technology, in combination with the Chinese word segmentation technology, a new mode of efficient semantic understanding can be provided for users, and the method plays an important role in intelligent questioning and answering, search recommendation and other systems in the specific application field.

Description

technical field [0001] The invention relates to a computer semantic analysis technology, in particular to a method for understanding the semantics of informational Chinese question sentences using semantic dependency analysis. Background technique [0002] Semantic understanding of sentences is an important research direction of natural language processing technology, and has been widely used in fields such as intelligent question answering. Due to the complexity of the Chinese language, it is difficult to understand questions and the progress is slow. At present, the semantic understanding methods of questions in intelligent question answering mainly include template method, keyword method, dependency parsing, semantic role labeling, etc. [0003] The template method classifies the questions entered by the user through a classifier. If they can be classified into these categories, they can be correctly converted and processed according to the templates corresponding to eac...

AI Technical Summary

Problems solved by technology

Chinese syntactic dependency analysis can achieve a complete analysis of the syntactic structure and relationship of input sentences, but because Chinese processing is more complex than English, there are problems such as fewer syntactic restrictions, and it is impossible to accurately mark specific tenses, passive voices, and prepositions without strong semantic instructions expression, etc.

Therefore, the semantic information of Chinese sentences cannot be fully expressed only through syntactic dependency analysis.

Semantic role annotation is aimed at the semantic role level of the argument, and has the disadvantage that it cannot cover the semantic relationship within the entire argument

Images