The webinar is held in German language.
The semantic search is a certain form of text search, which aims to deliver results that match the content. This means that it has to take into account the context of search terms, for example: If you are looking for the best bank to sit in, you probably do not mean a financial institution.
Semantic search methods are ubiquitous today - every time you search on Google, part of the results are ranked using semantic search.
Historically based semantic search mainly relied on expert knowledge that had to be written down in a structured form, so-called ontologies. For some time now, however, methods of artificial intelligence have been established in this field, which make the manual formalization of contexts obsolete. One of the most prominent examples is BERT - an architecture and training variant of neural networks published by Google in 2018, which enables a broad application without extensive pre-training.
In this webinar you will get an introduction to the application of BERT for Semantic Search using a real case study:
Every year millions of citizens interact with authorities and are regularly overwhelmed by the technical language used there. We have successfully used BERT to deliver the right answer from government documents with the help of colloquial queries - without the need for queries to use technical terms.
In the course of the seminar we will answer the following questions, among others:
- How does BERT for Semantic Search work?
- What problems can you solve with Semantic Search?
- What data do you need for it?