@inproceedings{wan-etal-2022-g,
title = "{G}-{MAP}: General Memory-Augmented Pre-trained Language Model for Domain Tasks",
author = "Wan, Zhongwei and
Yin, Yichun and
Zhang, Wei and
Shi, Jiaxin and
Shang, Lifeng and
Chen, Guangyong and
Jiang, Xin and
Liu, Qun",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.441",
doi = "10.18653/v1/2022.emnlp-main.441",
pages = "6585--6597",
abstract = "General pre-trained language models (PLMs), such as BERT, have achieved remarkable performance on various NLP tasks. Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this domain-adaptive pre-training (DAPT (CITATION)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a \textit{catastrophic forgetting} phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of \textbf{M}emory-\textbf{A}ugmented \textbf{P}re-trained Language Model (\textbf{MAP}), which augments the domain-specific PLM by a memory built from the frozen general PLM without losing the general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmentation strategies are explored to build memory and fusion memory into domain-specific PLM. We demonstrate the effectiveness of MAP on different domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed MAP can achieve SOTA results on these tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wan-etal-2022-g">
<titleInfo>
<title>G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhongwei</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichun</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lifeng</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guangyong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>General pre-trained language models (PLMs), such as BERT, have achieved remarkable performance on various NLP tasks. Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this domain-adaptive pre-training (DAPT (CITATION)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of Memory-Augmented Pre-trained Language Model (MAP), which augments the domain-specific PLM by a memory built from the frozen general PLM without losing the general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmentation strategies are explored to build memory and fusion memory into domain-specific PLM. We demonstrate the effectiveness of MAP on different domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed MAP can achieve SOTA results on these tasks.</abstract>
<identifier type="citekey">wan-etal-2022-g</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.441</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.441</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6585</start>
<end>6597</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks
%A Wan, Zhongwei
%A Yin, Yichun
%A Zhang, Wei
%A Shi, Jiaxin
%A Shang, Lifeng
%A Chen, Guangyong
%A Jiang, Xin
%A Liu, Qun
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F wan-etal-2022-g
%X General pre-trained language models (PLMs), such as BERT, have achieved remarkable performance on various NLP tasks. Recently, domain-specific PLMs have been proposed to boost the task performance of specific domains (e.g., biomedical and computer science) by continuing to pre-train general PLMs with domain-specific corpora. However, this domain-adaptive pre-training (DAPT (CITATION)) tends to forget the previous general knowledge acquired by general PLMs, which leads to a catastrophic forgetting phenomenon and sub-optimal performance. To alleviate this problem, we propose a new framework of Memory-Augmented Pre-trained Language Model (MAP), which augments the domain-specific PLM by a memory built from the frozen general PLM without losing the general knowledge. Specifically, we propose a new memory-augmented layer, and based on it, different augmentation strategies are explored to build memory and fusion memory into domain-specific PLM. We demonstrate the effectiveness of MAP on different domains (biomedical and computer science publications, news, and reviews) and different kinds (text classification, QA, NER) of tasks, and the extensive results show that the proposed MAP can achieve SOTA results on these tasks.
%R 10.18653/v1/2022.emnlp-main.441
%U https://aclanthology.org/2022.emnlp-main.441
%U https://doi.org/10.18653/v1/2022.emnlp-main.441
%P 6585-6597
Markdown (Informal)
[G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks](https://aclanthology.org/2022.emnlp-main.441) (Wan et al., EMNLP 2022)
ACL
- Zhongwei Wan, Yichun Yin, Wei Zhang, Jiaxin Shi, Lifeng Shang, Guangyong Chen, Xin Jiang, and Qun Liu. 2022. G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 6585–6597, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.