@inproceedings{liu-etal-2021-multi,
title = "Multi-stage Pre-training over Simplified Multimodal Pre-training Models",
author = "Liu, Tongtong and
Feng, Fangxiang and
Wang, Xiaojie",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.199/",
doi = "10.18653/v1/2021.acl-long.199",
pages = "2556--2565",
abstract = "Multimodal pre-training models, such as LXMERT, have achieved excellent results in downstream tasks. However, current pre-trained models require large amounts of training data and have huge model sizes, which make them impossible to apply in low-resource situations. How to obtain similar or even better performance than a larger model under the premise of less pre-training data and smaller model size has become an important problem. In this paper, we propose a new Multi-stage Pre-training (MSP) method, which uses information at different granularities from word, phrase to sentence in both texts and images to pre-train a model in stages. We also design several different pre-training tasks suitable for the information granularity in different stage in order to efficiently capture the diverse knowledge from a limited corpus. We take a Simplified LXMERT (LXMERT-S) which is with 45.9{\%} parameters of the original LXMERT model and only 11.44{\%} of the original pre-training data as the testbed of our MSP method. Experimental results show that our method achieves comparable performance to the original LXMERT model in all downstream tasks, and even outperforms the original model in Image-Text Retrieval task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-multi">
<titleInfo>
<title>Multi-stage Pre-training over Simplified Multimodal Pre-training Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tongtong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fangxiang</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Multimodal pre-training models, such as LXMERT, have achieved excellent results in downstream tasks. However, current pre-trained models require large amounts of training data and have huge model sizes, which make them impossible to apply in low-resource situations. How to obtain similar or even better performance than a larger model under the premise of less pre-training data and smaller model size has become an important problem. In this paper, we propose a new Multi-stage Pre-training (MSP) method, which uses information at different granularities from word, phrase to sentence in both texts and images to pre-train a model in stages. We also design several different pre-training tasks suitable for the information granularity in different stage in order to efficiently capture the diverse knowledge from a limited corpus. We take a Simplified LXMERT (LXMERT-S) which is with 45.9% parameters of the original LXMERT model and only 11.44% of the original pre-training data as the testbed of our MSP method. Experimental results show that our method achieves comparable performance to the original LXMERT model in all downstream tasks, and even outperforms the original model in Image-Text Retrieval task.</abstract>
<identifier type="citekey">liu-etal-2021-multi</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.199</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.199/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2556</start>
<end>2565</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-stage Pre-training over Simplified Multimodal Pre-training Models
%A Liu, Tongtong
%A Feng, Fangxiang
%A Wang, Xiaojie
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F liu-etal-2021-multi
%X Multimodal pre-training models, such as LXMERT, have achieved excellent results in downstream tasks. However, current pre-trained models require large amounts of training data and have huge model sizes, which make them impossible to apply in low-resource situations. How to obtain similar or even better performance than a larger model under the premise of less pre-training data and smaller model size has become an important problem. In this paper, we propose a new Multi-stage Pre-training (MSP) method, which uses information at different granularities from word, phrase to sentence in both texts and images to pre-train a model in stages. We also design several different pre-training tasks suitable for the information granularity in different stage in order to efficiently capture the diverse knowledge from a limited corpus. We take a Simplified LXMERT (LXMERT-S) which is with 45.9% parameters of the original LXMERT model and only 11.44% of the original pre-training data as the testbed of our MSP method. Experimental results show that our method achieves comparable performance to the original LXMERT model in all downstream tasks, and even outperforms the original model in Image-Text Retrieval task.
%R 10.18653/v1/2021.acl-long.199
%U https://aclanthology.org/2021.acl-long.199/
%U https://doi.org/10.18653/v1/2021.acl-long.199
%P 2556-2565
Markdown (Informal)
[Multi-stage Pre-training over Simplified Multimodal Pre-training Models](https://aclanthology.org/2021.acl-long.199/) (Liu et al., ACL-IJCNLP 2021)
ACL
- Tongtong Liu, Fangxiang Feng, and Xiaojie Wang. 2021. Multi-stage Pre-training over Simplified Multimodal Pre-training Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2556–2565, Online. Association for Computational Linguistics.