@inproceedings{lee-etal-2022-efficient-pre,
title = "Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking",
author = "Lee, Mingyu and
Park, Jun-Hyung and
Kim, Junho and
Kim, Kang-Min and
Lee, SangKeun",
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.502",
doi = "10.18653/v1/2022.emnlp-main.502",
pages = "7417--7427",
abstract = "Self-supervised pre-training has achieved remarkable success in extensive natural language processing tasks. Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations but comes at a substantial training cost. In this paper, we propose a novel concept-based curriculum masking (CCM) method to efficiently pre-train a language model. CCM has two key differences from existing curriculum learning approaches to effectively reflect the nature of MLM. First, we introduce a novel curriculum that evaluates the MLM difficulty of each token based on a carefully-designed linguistic difficulty criterion. Second, we construct a curriculum that masks easy words and phrases first and gradually masks related ones to the previously masked ones based on a knowledge graph. Experimental results show that CCM significantly improves pre-training efficiency. Specifically, the model trained with CCM shows comparative performance with the original BERT on the General Language Understanding Evaluation benchmark at half of the training cost.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lee-etal-2022-efficient-pre">
<titleInfo>
<title>Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingyu</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun-Hyung</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junho</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang-Min</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">SangKeun</namePart>
<namePart type="family">Lee</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>Self-supervised pre-training has achieved remarkable success in extensive natural language processing tasks. Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations but comes at a substantial training cost. In this paper, we propose a novel concept-based curriculum masking (CCM) method to efficiently pre-train a language model. CCM has two key differences from existing curriculum learning approaches to effectively reflect the nature of MLM. First, we introduce a novel curriculum that evaluates the MLM difficulty of each token based on a carefully-designed linguistic difficulty criterion. Second, we construct a curriculum that masks easy words and phrases first and gradually masks related ones to the previously masked ones based on a knowledge graph. Experimental results show that CCM significantly improves pre-training efficiency. Specifically, the model trained with CCM shows comparative performance with the original BERT on the General Language Understanding Evaluation benchmark at half of the training cost.</abstract>
<identifier type="citekey">lee-etal-2022-efficient-pre</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.502</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.502</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7417</start>
<end>7427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking
%A Lee, Mingyu
%A Park, Jun-Hyung
%A Kim, Junho
%A Kim, Kang-Min
%A Lee, SangKeun
%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 lee-etal-2022-efficient-pre
%X Self-supervised pre-training has achieved remarkable success in extensive natural language processing tasks. Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations but comes at a substantial training cost. In this paper, we propose a novel concept-based curriculum masking (CCM) method to efficiently pre-train a language model. CCM has two key differences from existing curriculum learning approaches to effectively reflect the nature of MLM. First, we introduce a novel curriculum that evaluates the MLM difficulty of each token based on a carefully-designed linguistic difficulty criterion. Second, we construct a curriculum that masks easy words and phrases first and gradually masks related ones to the previously masked ones based on a knowledge graph. Experimental results show that CCM significantly improves pre-training efficiency. Specifically, the model trained with CCM shows comparative performance with the original BERT on the General Language Understanding Evaluation benchmark at half of the training cost.
%R 10.18653/v1/2022.emnlp-main.502
%U https://aclanthology.org/2022.emnlp-main.502
%U https://doi.org/10.18653/v1/2022.emnlp-main.502
%P 7417-7427
Markdown (Informal)
[Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking](https://aclanthology.org/2022.emnlp-main.502) (Lee et al., EMNLP 2022)
ACL