← Search

Aaron Jaech

2 accepted papers

2022

Sparse Distillation: Speeding Up Text Classification by Using Bigger Student Models

NAACL 2022long

Distilling state-of-the-art transformer models into lightweight student models is an effective way to reduce computation cost at inference time. The student models are typically compact transformers with fewer parameters, while expensive operations such as self-attention persist. Therefore, the impr…

2021

Limitations of Autoregressive Models and Their Alternatives

NAACL 2021long

Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol. While this is attractive, it means they cannot model distributions whose next-symbol probability is hard to compute. Indeed, they cannot even model them well enough to solv…

Cited by 76SourcePDFScholar