@inproceedings{mitzalis-etal-2021-bertgen,
title = "{BERTG}en: Multi-task Generation through {BERT}",
author = "Mitzalis, Faidon and
Caglayan, Ozan and
Madhyastha, Pranava and
Specia, Lucia",
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.503",
doi = "10.18653/v1/2021.acl-long.503",
pages = "6440--6455",
abstract = "We present BERTGen, a novel, generative, decoder-only model which extends BERT by fusing multimodal and multilingual pre-trained models VL-BERT and M-BERT, respectively. BERTGen is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multi-task setting. With a comprehensive set of evaluations, we show that BERTGen outperforms many strong baselines across the tasks explored. We also show BERTGen{'}s ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGen substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mitzalis-etal-2021-bertgen">
<titleInfo>
<title>BERTGen: Multi-task Generation through BERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Faidon</namePart>
<namePart type="family">Mitzalis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ozan</namePart>
<namePart type="family">Caglayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranava</namePart>
<namePart type="family">Madhyastha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</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>We present BERTGen, a novel, generative, decoder-only model which extends BERT by fusing multimodal and multilingual pre-trained models VL-BERT and M-BERT, respectively. BERTGen is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multi-task setting. With a comprehensive set of evaluations, we show that BERTGen outperforms many strong baselines across the tasks explored. We also show BERTGen’s ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGen substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.</abstract>
<identifier type="citekey">mitzalis-etal-2021-bertgen</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.503</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.503</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>6440</start>
<end>6455</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BERTGen: Multi-task Generation through BERT
%A Mitzalis, Faidon
%A Caglayan, Ozan
%A Madhyastha, Pranava
%A Specia, Lucia
%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 mitzalis-etal-2021-bertgen
%X We present BERTGen, a novel, generative, decoder-only model which extends BERT by fusing multimodal and multilingual pre-trained models VL-BERT and M-BERT, respectively. BERTGen is auto-regressively trained for language generation tasks, namely image captioning, machine translation and multimodal machine translation, under a multi-task setting. With a comprehensive set of evaluations, we show that BERTGen outperforms many strong baselines across the tasks explored. We also show BERTGen’s ability for zero-shot language generation, where it exhibits competitive performance to supervised counterparts. Finally, we conduct ablation studies which demonstrate that BERTGen substantially benefits from multi-tasking and effectively transfers relevant inductive biases from the pre-trained models.
%R 10.18653/v1/2021.acl-long.503
%U https://aclanthology.org/2021.acl-long.503
%U https://doi.org/10.18653/v1/2021.acl-long.503
%P 6440-6455
Markdown (Informal)
[BERTGen: Multi-task Generation through BERT](https://aclanthology.org/2021.acl-long.503) (Mitzalis et al., ACL-IJCNLP 2021)
ACL
- Faidon Mitzalis, Ozan Caglayan, Pranava Madhyastha, and Lucia Specia. 2021. BERTGen: Multi-task Generation through BERT. 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 6440–6455, Online. Association for Computational Linguistics.