SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.13686 · ACL · 2021

AutoTinyBERT: Automatic Hyper-parameter Optimization for Efficient Pre-trained Language Models

Lifeng Shang, Xin Jiang, Xiao Chen, Qun Liu, Cheng Chen, Yichun Yin, Huawei Confidential

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Pre-trained language models (PLMs) have achieved great success in natural language processing. Most of PLMs follow the default setting of architecture hyper-parameters (e.g., the hidden dimension is a quarter of the intermediate dimension in feed-forward sub-networks) in BERT (Devlin et al., 2019). Few studies have been conducted to explore the design of architecture hyper-parameters in BERT, especially for the more efficient PLMs with tiny sizes, which are essential for practical deployment on resource-constrained devices. In this paper, we adopt the one-shot Neural Architecture Search (NAS) to automatically search architecture hyper-parameters. Specifically, we carefully design the techniques of one-shot learning and the search space to provide an adaptive and efficient development way of tiny PLMs for various latency constraints. We name our method AutoTinyBERT 1 and evaluate its effectiveness on the GLUE and SQuAD benchmarks. The extensive experiments show that our method outperforms both the SOTA searchbased baseline (NAS-BERT) and the SOTA distillation-based methods (such as DistilBERT, TinyBERT, MiniLM and MobileBERT). In addition, based on the obtained architectures, we propose a more efficient development method that is even faster than the development of a single PLM. * Contribution during internship at Noah's Ark Lab. 1 Our code implementation and pre-trained models are available at https://github.com/huawei-noah/ Pretrained-Language-Model .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2107.13686")
get_code_for_paper("2107.13686")
have("2107.13686")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2107.13686.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2107.13686.svg)](https://syntology.ai/paper/2107.13686)

Connect an agent — have() is free.