@inproceedings{zhang-etal-2024-languageflow,
title = "{L}anguage{F}low: Advancing Diffusion Language Generation with Probabilistic Flows",
author = "Zhang, Shujian and
Wu, Lemeng and
Gong, Chengyue and
Liu, Xingchao",
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.215",
pages = "3893--3905",
abstract = "Recent works have demonstrated success in controlling sentence attributes (e.g., sentiment) and structure (e.g., syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of starting from the noise and the learning steps has limited its implementation to many NLP real-world applications. This paper proposes Language Rectified Flow (LF).Our method is based on the reformulation of the standard probabilistic flow models.Language rectified flow learns (neural) ordinary differentialequation models to transport between the source distribution and the target distribution, henceproviding a unified and effective solution to generative modeling and domain transfer.From the source distribution, our language rectified flow yields fast simulation and effectively decreases the inference time. Experiments on three challenging fine-grained control tasks and multiple high-quality text editing show that our method consistently outperforms its baselines. Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-languageflow">
<titleInfo>
<title>LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shujian</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemeng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyue</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xingchao</namePart>
<namePart type="family">Liu</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>Recent works have demonstrated success in controlling sentence attributes (e.g., sentiment) and structure (e.g., syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of starting from the noise and the learning steps has limited its implementation to many NLP real-world applications. This paper proposes Language Rectified Flow (LF).Our method is based on the reformulation of the standard probabilistic flow models.Language rectified flow learns (neural) ordinary differentialequation models to transport between the source distribution and the target distribution, henceproviding a unified and effective solution to generative modeling and domain transfer.From the source distribution, our language rectified flow yields fast simulation and effectively decreases the inference time. Experiments on three challenging fine-grained control tasks and multiple high-quality text editing show that our method consistently outperforms its baselines. Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.</abstract>
<identifier type="citekey">zhang-etal-2024-languageflow</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.215</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>3893</start>
<end>3905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows
%A Zhang, Shujian
%A Wu, Lemeng
%A Gong, Chengyue
%A Liu, Xingchao
%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 zhang-etal-2024-languageflow
%X Recent works have demonstrated success in controlling sentence attributes (e.g., sentiment) and structure (e.g., syntactic structure) based on the diffusion language model. A key component that drives theimpressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While beneficial, the complexity of starting from the noise and the learning steps has limited its implementation to many NLP real-world applications. This paper proposes Language Rectified Flow (LF).Our method is based on the reformulation of the standard probabilistic flow models.Language rectified flow learns (neural) ordinary differentialequation models to transport between the source distribution and the target distribution, henceproviding a unified and effective solution to generative modeling and domain transfer.From the source distribution, our language rectified flow yields fast simulation and effectively decreases the inference time. Experiments on three challenging fine-grained control tasks and multiple high-quality text editing show that our method consistently outperforms its baselines. Extensive experiments and ablation studies demonstrate that our method can be general, effective, and beneficial for many NLP tasks.
%U https://aclanthology.org/2024.naacl-long.215
%P 3893-3905
Markdown (Informal)
[LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows](https://aclanthology.org/2024.naacl-long.215) (Zhang et al., NAACL 2024)
ACL
- Shujian Zhang, Lemeng Wu, Chengyue Gong, and Xingchao Liu. 2024. LanguageFlow: Advancing Diffusion Language Generation with Probabilistic Flows. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3893–3905, Mexico City, Mexico. Association for Computational Linguistics.