@inproceedings{wang-etal-2022-xlm,
title = "{XLM}-{D}: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation",
author = "Wang, Yong and
He, Shilin and
Chen, Guanhua and
Chen, Yun and
Jiang, Daxin",
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.466/",
doi = "10.18653/v1/2022.emnlp-main.466",
pages = "6934--6946",
abstract = "Pre-training language models have achieved thriving success in numerous natural language understanding and autoregressive generation tasks, but non-autoregressive generation in applications such as machine translation has not sufficiently benefited from the pre-training paradigm. In this work, we establish the connection between a pre-trained masked language model (MLM) and non-autoregressive generation on machine translation. From this perspective, we present XLM-D, which seamlessly transforms an off-the-shelf cross-lingual pre-training model into a non-autoregressive translation (NAT) model with a lightweight yet effective decorator. Specifically, the decorator ensures the representation consistency of the pre-trained model and brings only one additional trainable parameter. Extensive experiments on typical translation datasets show that our models obtain state-of-the-art performance while realizing the inference speed-up by 19.9x. One striking result is that on WMT14 En-De, our XLM-D obtains 29.80 BLEU points with multiple iterations, which outperforms the previous mask-predict model by 2.77 points."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-xlm">
<titleInfo>
<title>XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yong</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shilin</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanhua</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daxin</namePart>
<namePart type="family">Jiang</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>Pre-training language models have achieved thriving success in numerous natural language understanding and autoregressive generation tasks, but non-autoregressive generation in applications such as machine translation has not sufficiently benefited from the pre-training paradigm. In this work, we establish the connection between a pre-trained masked language model (MLM) and non-autoregressive generation on machine translation. From this perspective, we present XLM-D, which seamlessly transforms an off-the-shelf cross-lingual pre-training model into a non-autoregressive translation (NAT) model with a lightweight yet effective decorator. Specifically, the decorator ensures the representation consistency of the pre-trained model and brings only one additional trainable parameter. Extensive experiments on typical translation datasets show that our models obtain state-of-the-art performance while realizing the inference speed-up by 19.9x. One striking result is that on WMT14 En-De, our XLM-D obtains 29.80 BLEU points with multiple iterations, which outperforms the previous mask-predict model by 2.77 points.</abstract>
<identifier type="citekey">wang-etal-2022-xlm</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.466</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.466/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>6934</start>
<end>6946</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation
%A Wang, Yong
%A He, Shilin
%A Chen, Guanhua
%A Chen, Yun
%A Jiang, Daxin
%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 wang-etal-2022-xlm
%X Pre-training language models have achieved thriving success in numerous natural language understanding and autoregressive generation tasks, but non-autoregressive generation in applications such as machine translation has not sufficiently benefited from the pre-training paradigm. In this work, we establish the connection between a pre-trained masked language model (MLM) and non-autoregressive generation on machine translation. From this perspective, we present XLM-D, which seamlessly transforms an off-the-shelf cross-lingual pre-training model into a non-autoregressive translation (NAT) model with a lightweight yet effective decorator. Specifically, the decorator ensures the representation consistency of the pre-trained model and brings only one additional trainable parameter. Extensive experiments on typical translation datasets show that our models obtain state-of-the-art performance while realizing the inference speed-up by 19.9x. One striking result is that on WMT14 En-De, our XLM-D obtains 29.80 BLEU points with multiple iterations, which outperforms the previous mask-predict model by 2.77 points.
%R 10.18653/v1/2022.emnlp-main.466
%U https://aclanthology.org/2022.emnlp-main.466/
%U https://doi.org/10.18653/v1/2022.emnlp-main.466
%P 6934-6946
Markdown (Informal)
[XLM-D: Decorate Cross-lingual Pre-training Model as Non-Autoregressive Neural Machine Translation](https://aclanthology.org/2022.emnlp-main.466/) (Wang et al., EMNLP 2022)
ACL