Search Results for author:
Found 3 papers, 0 papers with code
DSFormer: Effective Compression of Text-Transformers by Dense-Sparse Weight Factorization
Extensive experiments on multiple natural language understanding benchmarks demonstrate that DSFormer obtains up to 40% better compression than the state-of-the-art low-rank factorizers, leading semi-structured sparsity baselines and popular knowledge distillation approaches.
Using Interventions to Improve Out-of-Distribution Generalization of Text-Matching Recommendation Systems
To explain this generalization failure, we consider an intervention-based importance metric, which shows that a fine-tuned model captures spurious correlations and fails to learn the causal features that determine the relevance between any two text inputs.
Extreme Regression for Dynamic Search Advertising
This paper also introduces a (3) new labelwise prediction algorithm in XReg useful for DSA and other recommendation tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
