@inproceedings{yuan-etal-2024-text,
title = "Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation",
author = "Yuan, Hongyi and
Yuan, Zheng and
Tan, Chuanqi and
Huang, Fei and
Huang, Songfang",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.2",
doi = "10.18653/v1/2024.naacl-long.2",
pages = "22--39",
abstract = "The diffusion model, a new generative modeling paradigm, has achieved great success in image, audio, and video generation.However, considering the discrete categorical nature of the text, it is not trivial to extend continuous diffusion models to natural language. In this work, we propose SeqDiffuSeq, a text diffusion model, to approach sequence-to-sequence text generation with an encoder-decoder Transformer architecture.To improve the generation performance, SeqDiffuSeq is equipped with the self-conditioning technique and our newly proposed adaptive noise schedule technique. Self-conditioning enables SeqDiffuSeq to better use the predicted sequence information during the generation process.The adaptive noise schedule balances the difficulty of denoising across time steps at the token level.Experiment results illustrate the improved performance on five sequence-to-sequence generation tasks compared to other diffusion-based models regarding text quality and inference time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2024-text">
<titleInfo>
<title>Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongyi</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuanqi</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songfang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The diffusion model, a new generative modeling paradigm, has achieved great success in image, audio, and video generation.However, considering the discrete categorical nature of the text, it is not trivial to extend continuous diffusion models to natural language. In this work, we propose SeqDiffuSeq, a text diffusion model, to approach sequence-to-sequence text generation with an encoder-decoder Transformer architecture.To improve the generation performance, SeqDiffuSeq is equipped with the self-conditioning technique and our newly proposed adaptive noise schedule technique. Self-conditioning enables SeqDiffuSeq to better use the predicted sequence information during the generation process.The adaptive noise schedule balances the difficulty of denoising across time steps at the token level.Experiment results illustrate the improved performance on five sequence-to-sequence generation tasks compared to other diffusion-based models regarding text quality and inference time.</abstract>
<identifier type="citekey">yuan-etal-2024-text</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.2</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.2</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>22</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation
%A Yuan, Hongyi
%A Yuan, Zheng
%A Tan, Chuanqi
%A Huang, Fei
%A Huang, Songfang
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F yuan-etal-2024-text
%X The diffusion model, a new generative modeling paradigm, has achieved great success in image, audio, and video generation.However, considering the discrete categorical nature of the text, it is not trivial to extend continuous diffusion models to natural language. In this work, we propose SeqDiffuSeq, a text diffusion model, to approach sequence-to-sequence text generation with an encoder-decoder Transformer architecture.To improve the generation performance, SeqDiffuSeq is equipped with the self-conditioning technique and our newly proposed adaptive noise schedule technique. Self-conditioning enables SeqDiffuSeq to better use the predicted sequence information during the generation process.The adaptive noise schedule balances the difficulty of denoising across time steps at the token level.Experiment results illustrate the improved performance on five sequence-to-sequence generation tasks compared to other diffusion-based models regarding text quality and inference time.
%R 10.18653/v1/2024.naacl-long.2
%U https://aclanthology.org/2024.naacl-long.2
%U https://doi.org/10.18653/v1/2024.naacl-long.2
%P 22-39
Markdown (Informal)
[Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation](https://aclanthology.org/2024.naacl-long.2) (Yuan et al., NAACL 2024)
ACL