@inproceedings{gu-tan-2022-non,
title = "Non-Autoregressive Sequence Generation",
author = "Gu, Jiatao and
Tan, Xu",
editor = "Benotti, Luciana and
Okazaki, Naoaki and
Scherrer, Yves and
Zampieri, Marcos",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-tutorials.4/",
doi = "10.18653/v1/2022.acl-tutorials.4",
pages = "21--27",
abstract = "Non-autoregressive sequence generation (NAR) attempts to generate the entire or partial output sequences in parallel to speed up the generation process and avoid potential issues (e.g., label bias, exposure bias) in autoregressive generation. While it has received much research attention and has been applied in many sequence generation tasks in natural language and speech, naive NAR models still face many challenges to close the performance gap between state-of-the-art autoregressive models because of a lack of modeling power. In this tutorial, we will provide a thorough introduction and review of non-autoregressive sequence generation, in four sections: 1) Background, which covers the motivation of NAR generation, the problem definition, the evaluation protocol, and the comparison with standard autoregressive generation approaches. 2) Method, which includes different aspects: model architecture, objective function, training data, learning paradigm, and additional inference tricks. 3) Application, which covers different tasks in text and speech generation, and some advanced topics in applications. 4) Conclusion, in which we describe several research challenges and discuss the potential future research directions. We hope this tutorial can serve both academic researchers and industry practitioners working on non-autoregressive sequence generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-tan-2022-non">
<titleInfo>
<title>Non-Autoregressive Sequence Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiatao</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luciana</namePart>
<namePart type="family">Benotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Non-autoregressive sequence generation (NAR) attempts to generate the entire or partial output sequences in parallel to speed up the generation process and avoid potential issues (e.g., label bias, exposure bias) in autoregressive generation. While it has received much research attention and has been applied in many sequence generation tasks in natural language and speech, naive NAR models still face many challenges to close the performance gap between state-of-the-art autoregressive models because of a lack of modeling power. In this tutorial, we will provide a thorough introduction and review of non-autoregressive sequence generation, in four sections: 1) Background, which covers the motivation of NAR generation, the problem definition, the evaluation protocol, and the comparison with standard autoregressive generation approaches. 2) Method, which includes different aspects: model architecture, objective function, training data, learning paradigm, and additional inference tricks. 3) Application, which covers different tasks in text and speech generation, and some advanced topics in applications. 4) Conclusion, in which we describe several research challenges and discuss the potential future research directions. We hope this tutorial can serve both academic researchers and industry practitioners working on non-autoregressive sequence generation.</abstract>
<identifier type="citekey">gu-tan-2022-non</identifier>
<identifier type="doi">10.18653/v1/2022.acl-tutorials.4</identifier>
<location>
<url>https://aclanthology.org/2022.acl-tutorials.4/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>21</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-Autoregressive Sequence Generation
%A Gu, Jiatao
%A Tan, Xu
%Y Benotti, Luciana
%Y Okazaki, Naoaki
%Y Scherrer, Yves
%Y Zampieri, Marcos
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F gu-tan-2022-non
%X Non-autoregressive sequence generation (NAR) attempts to generate the entire or partial output sequences in parallel to speed up the generation process and avoid potential issues (e.g., label bias, exposure bias) in autoregressive generation. While it has received much research attention and has been applied in many sequence generation tasks in natural language and speech, naive NAR models still face many challenges to close the performance gap between state-of-the-art autoregressive models because of a lack of modeling power. In this tutorial, we will provide a thorough introduction and review of non-autoregressive sequence generation, in four sections: 1) Background, which covers the motivation of NAR generation, the problem definition, the evaluation protocol, and the comparison with standard autoregressive generation approaches. 2) Method, which includes different aspects: model architecture, objective function, training data, learning paradigm, and additional inference tricks. 3) Application, which covers different tasks in text and speech generation, and some advanced topics in applications. 4) Conclusion, in which we describe several research challenges and discuss the potential future research directions. We hope this tutorial can serve both academic researchers and industry practitioners working on non-autoregressive sequence generation.
%R 10.18653/v1/2022.acl-tutorials.4
%U https://aclanthology.org/2022.acl-tutorials.4/
%U https://doi.org/10.18653/v1/2022.acl-tutorials.4
%P 21-27
Markdown (Informal)
[Non-Autoregressive Sequence Generation](https://aclanthology.org/2022.acl-tutorials.4/) (Gu & Tan, ACL 2022)
ACL
- Jiatao Gu and Xu Tan. 2022. Non-Autoregressive Sequence Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Tutorial Abstracts, pages 21–27, Dublin, Ireland. Association for Computational Linguistics.