The Berkeley NLP Group

Resources

The Berkeley Crossword Solver combines state-of-the-art QA with constraint solving.
The Berkeley Neural Parser infers syntactic annotations using neural networks and self-attention. We have an online demo!
The Berkeley Parser Analyser performs error analysis on parse trees.
The Berkeley Aligner aligns the words in multilingual parallel texts.
Ocular is a state-of-the-art historical document recognition system.

Interactive Assignments for Teaching Structured Neural NLP were developed for our graduate NLP course. They teach structured prediction using a combination of modern neural architectures and classic inference algorithms (in PyTorch and CoLab).
The Pac-Man projects are a set of class projects that teach foundational AI concepts, such as informed state-space search, probabilistic inference, and reinforcement learning.