all AI news
Understanding and Improving Compositional Generalization | AI2
Feb. 10, 2023, 7:21 p.m. | Allen Institute for AI
Allen Institute for AI www.youtube.com
Ben Bogin
Pre-trained language models perform well on a large variety of question-answering tasks, but they still often fail in the compositional generalization setup, where models are tested on unseen compositions of reasoning skills.
In this talk, I will go over three research directions that address this challenge. In the first part, I will show how we can improve generalization and interpretability with a compositional model architecture that recursively computes outputs and representations over grounded …
ai2 architecture challenge interpretability language language models part reasoning research setup skills talk trees understanding
More from www.youtube.com / Allen Institute for AI
Towards a more contextualized view of the web
2 weeks, 3 days ago |
www.youtube.com
Optimization within Latent Spaces
2 weeks, 3 days ago |
www.youtube.com
Training Human-AI Teams
2 weeks, 3 days ago |
www.youtube.com
LMQL Programming Large Language Models
1 month, 1 week ago |
www.youtube.com
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US