Financial event extraction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a financial event extraction method and device, electronic equipment and a storage medium. The method comprises the steps of: carrying out word segmentation on a to-be-extracted corpus through a Chinese word segmentation tool which introduces a financial knowledge graph; obtaining a first word vector of a word in the to-be-extracted corpus subjected to word segmentation processing and a second word vector of the word in the to-be-extracted corpus subjected to word segmentation processing based on a financial knowledge graph, and splicing the first word vector and the second word vector to obtain a third word vector of the word in the to-be-extracted corpus subjected to word segmentation processing; and based on the third word vector, predicting a predefined tag corresponding to the word in the to-be-extracted corpus subjected to word segmentation processing, and extracting a financial event according to the predefined tag corresponding to the word. According to the financial event extraction method and device, the electronic equipment and the storage medium of the embodiment of the invention, the precision of financial event extraction can be improved.

Description

technical field [0001] The present application relates to the technical field of event extraction, and in particular to a financial event extraction method, device, electronic equipment and storage medium. Background technique [0002] Event extraction is an important research direction in the field of information extraction. The so-called event extraction refers to presenting event information in unstructured text in a structured form. As a branch of event extraction, financial event extraction refers to extracting concise descriptions of financial events that have occurred from financial-related unstructured materials, such as research reports, news, etc., and the extracted event set can serve For higher-level applications, such as investment management analysis. The current financial event extraction is mostly based on the sequence labeling model, by defining the label system as (B, beginning, indicating the beginning of the event subject description; I, intermediate, in...

AI Technical Summary

Problems solved by technology

Although the existing solutions are suitable for most event extraction scenarios, in some specific fields, such as finance, the extraction accuracy needs to be improved

Images