@inproceedings{liang-etal-2022-janus,
title = "{JANUS}: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation",
author = "Liang, Xiaobo and
Wu, Lijun and
Li, Juntao and
Zhang, Min",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.550",
doi = "10.18653/v1/2022.emnlp-main.550",
pages = "8050--8060",
abstract = "Transformer-based autoregressive and non-autoregressive models have played an essential role in sequence generation tasks. The autoregressive model can obtain excellent performance, while the non-autoregressive model brings fast decoding speed for inference. In this paper, we propose \textbf{JANUS}, a \textbf{J}oint \textbf{A}utoregressive and \textbf{N}on-autoregressive training method using a\textbf{U}xiliary los\textbf{S} to enhance the model performance in both AR and NAR manner simultaneously and effectively alleviate the problem of distribution discrepancy.Further, we pre-train BART with JANUS on a large corpus with minimal cost (16 GPU days) and make the BART-JANUS capable of non-autoregressive generation, demonstrating that our approach can transfer the AR knowledge to NAR. Empirically, we show our approach and BART-JANUS can achieve significant improvement on multiple generation tasks, including machine translation and GLGE benchmarks. Our code is available at Github.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2022-janus">
<titleInfo>
<title>JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaobo</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijun</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transformer-based autoregressive and non-autoregressive models have played an essential role in sequence generation tasks. The autoregressive model can obtain excellent performance, while the non-autoregressive model brings fast decoding speed for inference. In this paper, we propose JANUS, a Joint Autoregressive and Non-autoregressive training method using aUxiliary losS to enhance the model performance in both AR and NAR manner simultaneously and effectively alleviate the problem of distribution discrepancy.Further, we pre-train BART with JANUS on a large corpus with minimal cost (16 GPU days) and make the BART-JANUS capable of non-autoregressive generation, demonstrating that our approach can transfer the AR knowledge to NAR. Empirically, we show our approach and BART-JANUS can achieve significant improvement on multiple generation tasks, including machine translation and GLGE benchmarks. Our code is available at Github.</abstract>
<identifier type="citekey">liang-etal-2022-janus</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.550</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.550</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>8050</start>
<end>8060</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation
%A Liang, Xiaobo
%A Wu, Lijun
%A Li, Juntao
%A Zhang, Min
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F liang-etal-2022-janus
%X Transformer-based autoregressive and non-autoregressive models have played an essential role in sequence generation tasks. The autoregressive model can obtain excellent performance, while the non-autoregressive model brings fast decoding speed for inference. In this paper, we propose JANUS, a Joint Autoregressive and Non-autoregressive training method using aUxiliary losS to enhance the model performance in both AR and NAR manner simultaneously and effectively alleviate the problem of distribution discrepancy.Further, we pre-train BART with JANUS on a large corpus with minimal cost (16 GPU days) and make the BART-JANUS capable of non-autoregressive generation, demonstrating that our approach can transfer the AR knowledge to NAR. Empirically, we show our approach and BART-JANUS can achieve significant improvement on multiple generation tasks, including machine translation and GLGE benchmarks. Our code is available at Github.
%R 10.18653/v1/2022.emnlp-main.550
%U https://aclanthology.org/2022.emnlp-main.550
%U https://doi.org/10.18653/v1/2022.emnlp-main.550
%P 8050-8060
Markdown (Informal)
[JANUS: Joint Autoregressive and Non-autoregressive Training with Auxiliary Loss for Sequence Generation](https://aclanthology.org/2022.emnlp-main.550) (Liang et al., EMNLP 2022)
ACL