Search Results for author:
Found 10 papers, 0 papers with code
Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models
A few large, homogenous, pre-trained models undergird many machine learning systems — and often, these models contain harmful stereotypes learned from the internet.
Conjugate Energy-Based Models
In this paper, we propose conjugate energy-based models (CEBMs), a new class of energy-based models that define a joint density over data and latent variables.
Unlocking Fairness: a Trade-off Revisited
The prevailing wisdom is that a model's fairness and its accuracy are in tension with one another.
Scaling Hierarchical Coreference with Homomorphic Compression
In this case, we need the representation to be a homomorphism so that the hash of unions and differences of sets can be computed directly from the hashes of operands.
Sketching for Latent Dirichlet-Categorical Models
We examine a related problem in which the parameters of a Bayesian model are very large and expensive to store in memory, and propose more compact representations of parameter values that can be used during inference.
Gradient-based Inference for Networks with Output Constraints
Practitioners apply neural networks to increasingly complex problems in natural language processing, such as syntactic parsing and semantic role labeling that have rich output structures.
