@inproceedings{hu-etal-2022-varmae,
title = "{V}ar{MAE}: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding",
author = "Hu, Dou and
Hou, Xiaolong and
Du, Xiyang and
Zhou, Mengyuan and
Jiang, Lianxin and
Mo, Yang and
Shi, Xiaofeng",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.468/",
doi = "10.18653/v1/2022.findings-emnlp.468",
pages = "6276--6286",
abstract = "Pre-trained language models have been widely applied to standard benchmarks. Due to the flexibility of natural language, the available resources in a certain domain can be restricted to support obtaining precise representation. To address this issue, we propose a novel Transformer-based language model named VarMAE for domain-adaptive language understanding. Under the masked autoencoding objective, we design a context uncertainty learning module to encode the token`s context into a smooth latent distribution. The module can produce diverse and well-formed contextual representations. Experiments on science- and finance-domain NLU tasks demonstrate that VarMAE can be efficiently adapted to new domains with limited resources."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2022-varmae">
<titleInfo>
<title>VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dou</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolong</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiyang</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengyuan</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lianxin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Mo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofeng</namePart>
<namePart type="family">Shi</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>Findings of the Association for Computational Linguistics: EMNLP 2022</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>Pre-trained language models have been widely applied to standard benchmarks. Due to the flexibility of natural language, the available resources in a certain domain can be restricted to support obtaining precise representation. To address this issue, we propose a novel Transformer-based language model named VarMAE for domain-adaptive language understanding. Under the masked autoencoding objective, we design a context uncertainty learning module to encode the token‘s context into a smooth latent distribution. The module can produce diverse and well-formed contextual representations. Experiments on science- and finance-domain NLU tasks demonstrate that VarMAE can be efficiently adapted to new domains with limited resources.</abstract>
<identifier type="citekey">hu-etal-2022-varmae</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.468</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.468/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6276</start>
<end>6286</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding
%A Hu, Dou
%A Hou, Xiaolong
%A Du, Xiyang
%A Zhou, Mengyuan
%A Jiang, Lianxin
%A Mo, Yang
%A Shi, Xiaofeng
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F hu-etal-2022-varmae
%X Pre-trained language models have been widely applied to standard benchmarks. Due to the flexibility of natural language, the available resources in a certain domain can be restricted to support obtaining precise representation. To address this issue, we propose a novel Transformer-based language model named VarMAE for domain-adaptive language understanding. Under the masked autoencoding objective, we design a context uncertainty learning module to encode the token‘s context into a smooth latent distribution. The module can produce diverse and well-formed contextual representations. Experiments on science- and finance-domain NLU tasks demonstrate that VarMAE can be efficiently adapted to new domains with limited resources.
%R 10.18653/v1/2022.findings-emnlp.468
%U https://aclanthology.org/2022.findings-emnlp.468/
%U https://doi.org/10.18653/v1/2022.findings-emnlp.468
%P 6276-6286
Markdown (Informal)
[VarMAE: Pre-training of Variational Masked Autoencoder for Domain-adaptive Language Understanding](https://aclanthology.org/2022.findings-emnlp.468/) (Hu et al., Findings 2022)
ACL