Exploring Dimensions and Chunking Strategies in Embedding Models

This podcast episode is all about semantic search and using embeddings to analyse text and social media data.

Dominik Weckmüller, a researcher at the Technical University of Dresden, talks about his PhD research, where he looks at how to analyze text with geographic references. 

He explains hyperloglog and embeddings, showing how these methods capture the meaning of text and can be used to search big databases without knowing the topics beforehand.

Here are the main points discussed:

1. Intro to Semantic Search and Hyperloglog: Looking at social media data by counting different users talking about specific topics in parks, while keeping privacy in mind.
2. Embeddings and Deep Learning Models: Turning text into numerical vectors (embeddings) to understand its meaning, allowing for advanced searches.
3. Application Examples: Using embeddings to search for things like emotions or activities in parks without needing predefined keywords.
4. Creating and Using Embeddings: Tools like transformers.js let you make embeddings on your computer, making it easy to analyze text.
5. Challenges and Innovations: Talking about how to explain the models, deal with long texts, and keep data private when using embeddings.
6. Future Directions: The potential for using embeddings with different media (like images and videos) and languages, plus the ongoing research in this fast-moving field.

Connect with Dominik Weckmüller here https://geo.rocks/

Stay up to date with AI here

https://huggingface.co/ Try searching for “map”  here https://huggingface.co/spaces

Check out this project I am working on 

https://quickmaptools.com/