Sentence Transformers and Embedding Evaluation – Talking Language AI Ep#3 Full episode:
https://youtu.be/apuDeylm1uE
About The Speaker:
Nils is the creator of Sentence-BERT and has authored several well-known research papers, including Sentence-BERT and the popular Sentence Transformers library. He’s also worked as a Research Scientist at HuggingFace, (co-)founded several web companies, and worked as an AI consultant in the area of investment banking, media, and IoT.
===
In our conversation, Nils gives us an introduction to the Sentence-BERT package and the large language models provided in it. He also shares some lessons from his experience in open-source development of such a popular package. Finally, Nils touches on his research collaborations on how to evaluate embeddings through works like MTEB: Massive Text Embedding Benchmark and BEIR.
To go deeper into these tools, and other concepts around embeddings, watch the video and join the conversation on Discord. Stay tuned for more episodes in our Talking Language AI series!
===
Join the Cohere Discord: https://discord.gg/co-mmunity
Discussion thread for this episode (feel free to ask questions):
https://discord.com/channels/954421988141711382/1052547510910062624
Watch more episodes of Talking Language AI: https://www.youtube.com/playlist?list=PLLalUvky4CLJ9ZgtZguDJ7dAYuI1bfaYW
===
Resources:
Bonjour. مرحبا. Guten tag. Hola. Cohere’s Multilingual Text Understanding Model is Now Available: https://txt.cohere.ai/multilingual/
SBERT: https://www.sbert.net/
SBERT Paper: https://arxiv.org/abs/1908.10084
MTEB: Massive Text Embedding Benchmark: https://arxiv.org/abs/2210.07316
BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models: https://openreview.net/forum?id=wCu6T5xFjeJ
SetFit – Efficient Few-shot Learning with Sentence Transformers https://github.com/huggingface/setfit
Add comment