Entity relationship extraction method, device, electronic device and storage medium

Abstract

The embodiment of the present invention relates to an entity relationship extraction method, device, electronic equipment, and storage medium. The method includes: performing word segmentation processing on the target text to be extracted to obtain multiple words; performing part-of-speech tagging on each of the words to obtain The part-of-speech tag of each of the words; based on the part-of-speech tag of each of the words, the target text is subjected to a dependency syntax analysis to obtain a dependency syntax tree of the target text; based on the dependency syntax tree, the target text is determined a corresponding syntactic pattern, and extracting entity-relationship triples from the target text based on the syntactic pattern. Thus, it is possible to efficiently and accurately extract entity-relationship triples from corpus data.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of natural language processing, and in particular, relate to an entity relationship extraction method, device, electronic equipment, and storage medium. Background technique [0002] With the development of the Internet, a large number of different forms of Internet data are generated every day in various fields. How to accurately and efficiently mine important information in Internet data to improve service efficiency in this field is a key issue. Furthermore, in information mining, entity relationship extraction is one of the core tasks. At present, commonly used entity relationship extraction methods include rule-based entity relationship extraction methods, dictionary-based entity relationship extraction methods, and machine learning-based entity relationship extraction methods. [0003] Among them, for the rule-based entity relationship extraction method, the emphasis is on the de...

AI Technical Summary

Problems solved by technology

However, different fields have different expertise, therefore, the rules formulated for a certain field cannot be transplanted to other fields, which leads to the poor portability of the rule-based entity relationship extraction method; for the dictionary-based entity relationship The extraction method, because it can only identify the relationship between entities in sentences with verbs as the central word, it is difficult to realize the identification and reasoning of relational structures such as synonyms and antonyms, and it is difficult to solve the relationship extraction of words outside the dictionary. Therefore, the dictionary-based entity relationship extraction method is very inflexible; for the machine learning-based entity relationship extraction method, the accuracy and recall rate of machine learning results are highly dependent on the labeled corpus, and strong manual intervention is required , and corpus annotation is time-consuming and labor-intensive, which leads to a long overall development cycle of the entity relationship extraction method based on machine learning, and requires high manpower and material resources

Images