Non-limiting relationship mining method based on dependency syntax and pattern rule

Abstract

The present invention discloses a non-limiting relationship mining method based on dependency syntax and a pattern rule. The method comprises the following steps: step one, performing word segmentation and part-of-speech tagging; step two, performing entity identification; step three, performing dependency syntax analysis; step four, performing entity relationship mining; and step five, obtaininga relationship mining comprehensive result. According to the method disclosed by the present invention, semantic information extraction of large-scale unstructured or semi-structured texts can be realized, automatic extraction of an entity relationship can be realized, entity relationship information can be effectively mined from a large number of texts, and business application value can be enhanced.

Description

technical field [0001] The invention relates to the technical field of natural language processing applications, in particular to an unrestricted relationship mining method based on dependency syntax and pattern rules. Background technique [0002] With the development of the Internet and big data technology, the number of users is increasing, and the network is full of various information. On the one hand, massive amounts of information necessarily contain rich and effective information, among which entity relationship is a very valuable information. For example, the relationship between a person and an institution appearing in network information. On the other hand, the rapid increase in the amount of information and types of information has also caused the evolution of relationship types. The traditional supervised relationship extraction method is relatively narrow (supervised relationship extraction generally needs to determine in advance which entity relationships exi...

AI Technical Summary

Problems solved by technology

On the other hand, the rapid increase in the amount of information and types of information has also caused the evolution of relationship types. The traditional supervised relationship extraction method is relatively narrow (supervised relationship extraction generally needs to determine in advance which entity relationships exist in the information, and at the same time requires a large number of Human-labeled relational corpus), which cannot cover all relational types

At present, there is an open bootstrapped relationship mining method, which mainly uses regular expressions for relationship mining on the basis of words, but manually establishes a large number of regular expressions or rule sets in advance to cover as many text types as possible.

Images