PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
Jul 12, 2020
Sprecher:innen
Saurabh Goyal
Sprecher:in · 0 Follower:innen
Anamitra Roy Choudhury
Sprecher:in · 0 Follower:innen
Souhabh M. Raje
Sprecher:in · 0 Follower:innen
Venkatesan T. Chakaravarthy
Sprecher:in · 0 Follower:innen
Yogish Sabharwal
Sprecher:in · 0 Follower:innen
Ashish Verma
Sprecher:in · 0 Follower:innen
Über
We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pertaining to word-vectors (intermediate encoder outputs) and eliminating the redundant vectors. b) determining which word-vectors to eliminate by developing a strategy for measuring their significance, based on the self-attention mechanism; c) learning how many word-vectors to eliminate by augmenting the BERT model and the loss function. Experiments on the standard GLUE benchmark shows that PoWER-BERT achieves up to 4.5x reduction in inference time over BERT with < 1 loss in accuracy. We show that PoWER-BERT offers significantly better trade-off between accuracy and inference time compared to prior methods. We demonstrate that our method attains up to 6.8x reduction in inference time with < 1 loss in accuracy when applied over ALBERT, a highly compressed version of BERT.We develop a novel method, called PoWER-BERT, for improving the inference time of the popular BERT model, while maintaining the accuracy. It works by: a) exploiting redundancy pertaining to word-vectors (intermediate encoder outputs) and eliminating the redundant vectors. b) determining which word-vectors to eliminate by developing a strategy for measuring their significance, based on the self-attention mechanism; c) learning how many word-vectors to eliminate by augmenting the BERT model and t…
Kategorien
KI und Datenwissenschaft
Kategorie · 10,8k Präsentationen
Über ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
The Effect of Natural Distribution Shift on Question Answering Models
Später ansehen
John Miller, …
Task Understanding from Confusing Mulit-task Data
Später ansehen
Xin Su, …
Black-Box Methods for Restoring Monotonicity
Später ansehen
Graph Clustering with Graph Neural Networks
Später ansehen
Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
Später ansehen
Kaixuan Wei, …
The Sample Complexity of Best-k Items Selection from Pairwise Comparisons
Später ansehen
Wenbo Ren, …