Work

EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference

Year: 2021

Type: conference-paper

Abstract: Transformer-based language models such as BERT provide significant accuracy improvement to a multitude of natural language processing (NLP) tasks. However, their hefty computational and memory demands make them challenging to deploy to resource-constrained edge platforms with strict latency requirements.

Source: IEEE/ACM International Symposium on Microarchitecture (MICRO)

DOI: 10.1145/3466752.3480095

Authors: Thierry Tambe, Coleman Hooper, Lillian Pentecost, Tianyu Jia, En-Yu Yang, Marco Donato, Victor Sanh, Paul Whatmough, Alexander M. Rush, David Brooks, Gu-Yeon Wei

Institutions: Harvard University, Tufts University, Hugging Face, Cornell University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Semiconductor Research Corporation, Defense Advanced Research Projects Agency

Awards: CSR: SMALL: Virtualized Accelerators for Scalable, Composable Architectures, SHF: Medium: A Cloudless Universal Translator, G8724954132, G8782647

OpenAlex ID: W3207622241

FWCI: 6.123

Cites: 93

Cited by: 145

Related to: 10