In this infodemic era, fact-checking is becoming a vital task. However, it is a complex and time-consuming activity.

In this talk, we will see how to combine Information Retrieval tools with modern Language Models to simply implement a fact-checking baseline with low human effort.

I will show you how to build a funny use case around rock music.

The application is based on several Python open-source libraries: Haystack, FAISS, Hugging Face Transformers, Sentence Transformers.
This step-by-step implementation will be an opportunity to learn more about Dense retrieval and Natural Language Inference models in a hands-on way. I will share some insights into developing modern Natural Language applications.

Why it's relevant:

Fact-checking is significant to the society, although it is still difficult to do automatically. Using modern NLP tools can help speed up and automate part of this task.

What the audience will learn:
- Dense retrieval for semantic search
- Natural Language Inference models
- How to build a fact-checking system using Haystack, FAISS, Hugging Face Transformers, Sentence Transformers.
- How to integrate powerful (Large) Language Models in your NLP applications, conditioning them to operate on your knowledge base
- How to efficiently combine tools from Information Retrieval, NLP, and Vector Search