Group assignment 3
Portfolio Exercise 3:
Introduction
Task
Create something cool 🚀 using SBERT and semantic search or perhaps more?! That’s a bit of a vague description but there are many options.
- You are welcome to use images and CLIP
- You can also use SetFit for supervised tasks with SBERT models.
Here are some projects for inspiration:
some more ideas:
- get some podcast transcripts for a specific topic (or create transcripts with Whisper - search for OpenAI Whisper Colab)
- Finetune an SBERT model using domain adaptation
- Embed and build a search engine
- Build a Gradio app
Feel free to choose any of these ideas or come up with your own. The goal is to use SBERT and semantic search (or other techniques) to create something interesting and useful.
Data
- 🤗 datasets
- Kaggle
- make your own
Delivery
- Create a github repository (or use the existing one and adapt it)
- Create a Gradio demo of the model in inference mode
- Save colab notebook in the github.
- Provide a readme.md with brief description.
- Submission can be in groups up to 3.
- Submit by sending an email with link to repo to Hamid (hamidb@business.aau.dk) with Daniel & Roman in cc. (dsh@…, roman@…)