Thu Feb 09 2023
Wed Feb 08 2023

GPTScore: Evaluate as You Desire

Generative models
Machine learning
Natural language processing
Natural language processing
Text generation
Artificial intelligence

Proposes a novel evaluation framework, GPTSCORE, which utilizes the emergent abilities (e.g., zero-shot instruction) from generative pre-trained models to score generated texts.

Provides a new evaluation framework for generated texts that utilizes pre-trained models to achieve customized, multi-faceted evaluation without the need for annotated samples. The approach can effectively allow businesses to assess the quality of generated text.

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

Regularization methods
Machine learning
Deep learning
Image recognition
Speech recognition
Deep learning

Develops a practical, memory-efficient algorithm which approximately recovers Shampoo performance in three modern DL settings (ImageNet, Librispeech, etc).

Introduces a low-rank sketching approach to adaptive regularization methods in deep learning tasks, reducing memory and compute requirements of maintaining a matrix preconditioner. The method performs well in large scale benchmarks such as ImageNet and Librispeech.

Mon Feb 06 2023
Sun Feb 05 2023
Thu Feb 02 2023
Wed Feb 01 2023