@inproceedings{wang-etal-2021-mention,
title = "Mention Flags ({MF}): Constraining Transformer-based Text Generators",
author = "Wang, Yufei and
Wood, Ian and
Wan, Stephen and
Dras, Mark and
Johnson, Mark",
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.9",
doi = "10.18653/v1/2021.acl-long.9",
pages = "103--113",
abstract = "This paper focuses on Seq2Seq (S2S) constrained text generation where the text generator is constrained to mention specific words which are inputs to the encoder in the generated outputs. Pre-trained S2S models or a Copy Mechanism are trained to copy the surface tokens from encoders to decoders, but they cannot guarantee constraint satisfaction. Constrained decoding algorithms always produce hypotheses satisfying all constraints. However, they are computationally expensive and can lower the generated text quality. In this paper, we propose Mention Flags (MF), which traces whether lexical constraints are satisfied in the generated outputs in an S2S decoder. The MF models can be trained to generate tokens in a hypothesis until all constraints are satisfied, guaranteeing high constraint satisfaction. Our experiments on the Common Sense Generation task (CommonGen) (Lin et al., 2020), End2end Restaurant Dialog task (E2ENLG) (Du{\v{}}sek et al., 2020) and Novel Object Captioning task (nocaps) (Agrawal et al., 2019) show that the MF models maintain higher constraint satisfaction and text quality than the baseline models and other constrained decoding algorithms, achieving state-of-the-art performance on all three tasks. These results are achieved with a much lower run-time than constrained decoding algorithms. We also show that the MF models work well in the low-resource setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-mention">
<titleInfo>
<title>Mention Flags (MF): Constraining Transformer-based Text Generators</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Wood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Dras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Johnson</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>This paper focuses on Seq2Seq (S2S) constrained text generation where the text generator is constrained to mention specific words which are inputs to the encoder in the generated outputs. Pre-trained S2S models or a Copy Mechanism are trained to copy the surface tokens from encoders to decoders, but they cannot guarantee constraint satisfaction. Constrained decoding algorithms always produce hypotheses satisfying all constraints. However, they are computationally expensive and can lower the generated text quality. In this paper, we propose Mention Flags (MF), which traces whether lexical constraints are satisfied in the generated outputs in an S2S decoder. The MF models can be trained to generate tokens in a hypothesis until all constraints are satisfied, guaranteeing high constraint satisfaction. Our experiments on the Common Sense Generation task (CommonGen) (Lin et al., 2020), End2end Restaurant Dialog task (E2ENLG) (Dušek et al., 2020) and Novel Object Captioning task (nocaps) (Agrawal et al., 2019) show that the MF models maintain higher constraint satisfaction and text quality than the baseline models and other constrained decoding algorithms, achieving state-of-the-art performance on all three tasks. These results are achieved with a much lower run-time than constrained decoding algorithms. We also show that the MF models work well in the low-resource setting.</abstract>
<identifier type="citekey">wang-etal-2021-mention</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.9</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.9</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>103</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mention Flags (MF): Constraining Transformer-based Text Generators
%A Wang, Yufei
%A Wood, Ian
%A Wan, Stephen
%A Dras, Mark
%A Johnson, Mark
%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 wang-etal-2021-mention
%X This paper focuses on Seq2Seq (S2S) constrained text generation where the text generator is constrained to mention specific words which are inputs to the encoder in the generated outputs. Pre-trained S2S models or a Copy Mechanism are trained to copy the surface tokens from encoders to decoders, but they cannot guarantee constraint satisfaction. Constrained decoding algorithms always produce hypotheses satisfying all constraints. However, they are computationally expensive and can lower the generated text quality. In this paper, we propose Mention Flags (MF), which traces whether lexical constraints are satisfied in the generated outputs in an S2S decoder. The MF models can be trained to generate tokens in a hypothesis until all constraints are satisfied, guaranteeing high constraint satisfaction. Our experiments on the Common Sense Generation task (CommonGen) (Lin et al., 2020), End2end Restaurant Dialog task (E2ENLG) (Dušek et al., 2020) and Novel Object Captioning task (nocaps) (Agrawal et al., 2019) show that the MF models maintain higher constraint satisfaction and text quality than the baseline models and other constrained decoding algorithms, achieving state-of-the-art performance on all three tasks. These results are achieved with a much lower run-time than constrained decoding algorithms. We also show that the MF models work well in the low-resource setting.
%R 10.18653/v1/2021.acl-long.9
%U https://aclanthology.org/2021.acl-long.9
%U https://doi.org/10.18653/v1/2021.acl-long.9
%P 103-113
Markdown (Informal)
[Mention Flags (MF): Constraining Transformer-based Text Generators](https://aclanthology.org/2021.acl-long.9) (Wang et al., ACL-IJCNLP 2021)
ACL
- Yufei Wang, Ian Wood, Stephen Wan, Mark Dras, and Mark Johnson. 2021. Mention Flags (MF): Constraining Transformer-based Text Generators. 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 103–113, Online. Association for Computational Linguistics.