Entity relationship rapid extraction method based on automaton

Abstract

The invention provides an entity relationship rapid extraction method based on an automaton. The entity relationship rapid extraction method comprises the following steps: step 1, customizing a rule file; step 2, performing grammar checking on each rule in the rule file, and detecting whether the rules in the rule file meet grammar requirements or not; if so, executing step 3; step 3, performing semantic interpretation on each rule in the rule file through grammar checking; step 4, analyzing and compiling each rule in the rule file subjected to the semantic interpretation to finish conversion from the rule to a stacked finite-state automaton, so as to obtain the finite-state automaton; step 5, extracting an entity attribute and an entity relationship from input text data by utilizing the finite-state automaton, so as to obtain a final entity attribute and entity relationship. The entity relationship rapid extraction method based on the automaton has the advantages that the rapid extraction of the entity attribute and the entity relationship of open domain texts can be carried out. Meanwhile, the entity relationship of a specific field can be subjected to customized extraction.

Description

technical field [0001] The invention belongs to the technical field of entity relationship extraction in open domain texts, and in particular relates to an automata-based rapid entity relationship extraction method. Background technique [0002] With the explosive development of the Internet, the data on the Internet is increasing exponentially. There is a wealth of information in the huge mass of data. However, the original unstructured or semi-structured web pages, documents, Weibo, multimedia and other formats of data cannot directly provide us with the precise information we want. Therefore, information extraction techniques for open domain texts are becoming more and more important. Named entities are often the carrier of important information contained in text, so the extraction of named entities and entity relationships is an important information extraction technology. For example, using the extracted named entities and entity relationships, a person file system c...

AI Technical Summary

Problems solved by technology

[0004] Among the existing entity relationship extraction methods, the rule-based method has good accuracy, but the quality of the rules is directly related to the quality of the entity relationship extraction results, so writing the rules requires expert experience, and the rules generally depend on the field. Therefore rule portability is also a major challenge

Statistics-based methods usually extract content in a certain field, which has great limitations for entity relationship recognition in open-domain texts; and the model decoding speed of statistical-based extraction methods will be relatively slow

Therefore, the existing technology is difficult to fully meet the requirements of fast and high portability of the entity relationship extraction method

Images