2 papers
cs.LG2024
Controllable Generation via Locally Constrained Resampling
Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck
Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs…
cs.LG2024
Semantic Loss Functions for Neuro-Symbolic Structured Prediction
Kareem Ahmed, Stefano Teso, Paolo Morettin +8
Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the in…