An Improved Method for Class-specific Keyword Extraction: A Case Study in the German Business Registry

TL;DR

This paper introduces an enhanced class-specific keyword extraction method based on KeyBERT, tailored for German business registry data, significantly outperforming previous approaches in classifying economic sectors.

Contribution

The paper presents a novel improvement to KeyBERT for extracting class-specific keywords, specifically applied to German business registry entries for economic sector classification.

Findings

Significant performance improvement over previous methods

Effective identification of class-specific keywords

Set new standards for class-specific keyword extraction

Abstract

The task of $\textit{keyword extraction}$ is often an important initial step in unsupervised information extraction, forming the basis for tasks such as topic modeling or document classification. While recent methods have proven to be quite effective in the extraction of keywords, the identification of $\textit{class-specific}$ keywords, or only those pertaining to a predefined class, remains challenging. In this work, we propose an improved method for class-specific keyword extraction, which builds upon the popular $\textbf{KeyBERT}$ library to identify only keywords related to a class described by $\textit{seed keywords}$. We test this method using a dataset of German business registry entries, where the goal is to classify each business according to an economic sector. Our results reveal that our method greatly improves upon previous approaches, setting a new standard for $\textit{class-specific}$ keyword extraction.