@inproceedings{chen-etal-2020-recall,
title = "Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting",
author = "Chen, Sanyuan and
Hou, Yutai and
Cui, Yiming and
Che, Wanxiang and
Liu, Ting and
Yu, Xiangzhan",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.634",
doi = "10.18653/v1/2020.emnlp-main.634",
pages = "7870--7881",
abstract = "Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal performance. To fine-tune with less forgetting, we propose a recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks. Specifically, we introduce a Pretraining Simulation mechanism to recall the knowledge from pretraining tasks without data, and an Objective Shifting mechanism to focus the learning on downstream tasks gradually. Experiments show that our method achieves state-of-the-art performance on the GLUE benchmark. Our method also enables BERT-base to achieve better average performance than directly fine-tuning of BERT-large. Further, we provide the open-source RecAdam optimizer, which integrates the proposed mechanisms into Adam optimizer, to facility the NLP community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-recall">
<titleInfo>
<title>Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanyuan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yutai</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Cui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangzhan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal performance. To fine-tune with less forgetting, we propose a recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks. Specifically, we introduce a Pretraining Simulation mechanism to recall the knowledge from pretraining tasks without data, and an Objective Shifting mechanism to focus the learning on downstream tasks gradually. Experiments show that our method achieves state-of-the-art performance on the GLUE benchmark. Our method also enables BERT-base to achieve better average performance than directly fine-tuning of BERT-large. Further, we provide the open-source RecAdam optimizer, which integrates the proposed mechanisms into Adam optimizer, to facility the NLP community.</abstract>
<identifier type="citekey">chen-etal-2020-recall</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.634</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.634</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>7870</start>
<end>7881</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting
%A Chen, Sanyuan
%A Hou, Yutai
%A Cui, Yiming
%A Che, Wanxiang
%A Liu, Ting
%A Yu, Xiangzhan
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F chen-etal-2020-recall
%X Deep pretrained language models have achieved great success in the way of pretraining first and then fine-tuning. But such a sequential transfer learning paradigm often confronts the catastrophic forgetting problem and leads to sub-optimal performance. To fine-tune with less forgetting, we propose a recall and learn mechanism, which adopts the idea of multi-task learning and jointly learns pretraining tasks and downstream tasks. Specifically, we introduce a Pretraining Simulation mechanism to recall the knowledge from pretraining tasks without data, and an Objective Shifting mechanism to focus the learning on downstream tasks gradually. Experiments show that our method achieves state-of-the-art performance on the GLUE benchmark. Our method also enables BERT-base to achieve better average performance than directly fine-tuning of BERT-large. Further, we provide the open-source RecAdam optimizer, which integrates the proposed mechanisms into Adam optimizer, to facility the NLP community.
%R 10.18653/v1/2020.emnlp-main.634
%U https://aclanthology.org/2020.emnlp-main.634
%U https://doi.org/10.18653/v1/2020.emnlp-main.634
%P 7870-7881
Markdown (Informal)
[Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting](https://aclanthology.org/2020.emnlp-main.634) (Chen et al., EMNLP 2020)
ACL