We're sorry but this page doesn't work properly without JavaScript enabled. Please enable it to continue.
Feedback

Fact Checking Rocks: how to build a fact-checking system

Formal Metadata

Title
Fact Checking Rocks: how to build a fact-checking system
Title of Series
Number of Parts
60
Author
Contributors
License
CC Attribution 3.0 Unported:
You are free to use, adapt and copy, distribute and transmit the work or content in adapted or unchanged form for any legal purpose as long as the work is attributed to the author in the manner specified by the author or licensor.
Identifiers
Publisher
Release Date2023
LanguageEnglish

Content Metadata

Subject Area
Genre
Abstract
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