Public administration in Germany suffers from a shortage of young talent. According to a McKinsey study, this shortage will amount to 731.000 employees by 2030. At the same time, public authorities are often recognized as old fashioned regarding their work processes. Digitalizing public services could save costs, reduce waiting times and maintain a satisfactory service level even with a reduced number of employees. One burden to overcome is the administrative jargon which is often not intuitive to citizens.

The automation of public and governmental services requires an user interface, where users can query their needs and the service provides all related relevant information. This can be quite challenging, since the user queries contain informal formulations of the customer needs, which may differ strongly from the administrative jargon. Thus, the automated service has to unterstand the meaning of the queries and translate them to administrative jargon.

For example, the registration of a business requires an industry code, for which the automated service should understand the relation between the business purpose entered by the client and the descriptions of different industry codes. For example, if a user wants to register a beauty salon, he/she could enter "I lacquer nails" and should find the right business code for beauty salons.

This is especially challenging if a business code is including a number of very diverse services. For instance, the business code "Miscellaneous other services" includes piercing studios as well as facility management. Traditional keyword based approaches are therefore not promising to deliver good results.

The intention of the user queries can be resolved by implementing a model based on the pre-trained BERT model (bidirectional encoder representations from transformers), developed by Google. The key advantage of the BERT model is, that it is able to recognize semantically similar words and expressions by considering their context. The base model is then further specialized for the specific context by training on problem- and domain-specific labeled data, such as user queries and their respective correct business code.