@inproceedings{xu-etal-2020-mixed,
title = "Mixed-Lingual Pre-training for Cross-lingual Summarization",
author = "Xu, Ruochen and
Zhu, Chenguang and
Shi, Yu and
Zeng, Michael and
Huang, Xuedong",
editor = "Wong, Kam-Fai and
Knight, Kevin and
Wu, Hua",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.53/",
doi = "10.18653/v1/2020.aacl-main.53",
pages = "536--541",
abstract = "Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate -{\ensuremath{>}} summarize or summarize -{\ensuremath{>}} translate. Recently, end-to-end models have achieved better results, but these approaches are mostly limited by their dependence on large-scale labeled data. We propose a solution based on mixed-lingual pre-training that leverages both cross-lingual tasks such as translation and monolingual tasks like masked language models. Thus, our model can leverage the massive monolingual data to enhance its modeling of language. Moreover, the architecture has no task-specific components, which saves memory and increases optimization efficiency. We show in experiments that this pre-training scheme can effectively boost the performance of cross-lingual summarization. In NCLS dataset, our model achieves an improvement of 2.82 (English to Chinese) and 1.15 (Chinese to English) ROUGE-1 scores over state-of-the-art results."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2020-mixed">
<titleInfo>
<title>Mixed-Lingual Pre-training for Cross-lingual Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruochen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenguang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuedong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate -\ensuremath> summarize or summarize -\ensuremath> translate. Recently, end-to-end models have achieved better results, but these approaches are mostly limited by their dependence on large-scale labeled data. We propose a solution based on mixed-lingual pre-training that leverages both cross-lingual tasks such as translation and monolingual tasks like masked language models. Thus, our model can leverage the massive monolingual data to enhance its modeling of language. Moreover, the architecture has no task-specific components, which saves memory and increases optimization efficiency. We show in experiments that this pre-training scheme can effectively boost the performance of cross-lingual summarization. In NCLS dataset, our model achieves an improvement of 2.82 (English to Chinese) and 1.15 (Chinese to English) ROUGE-1 scores over state-of-the-art results.</abstract>
<identifier type="citekey">xu-etal-2020-mixed</identifier>
<identifier type="doi">10.18653/v1/2020.aacl-main.53</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.53/</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>536</start>
<end>541</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mixed-Lingual Pre-training for Cross-lingual Summarization
%A Xu, Ruochen
%A Zhu, Chenguang
%A Shi, Yu
%A Zeng, Michael
%A Huang, Xuedong
%Y Wong, Kam-Fai
%Y Knight, Kevin
%Y Wu, Hua
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 December
%I Association for Computational Linguistics
%C Suzhou, China
%F xu-etal-2020-mixed
%X Cross-lingual Summarization (CLS) aims at producing a summary in the target language for an article in the source language. Traditional solutions employ a two-step approach, i.e. translate -\ensuremath> summarize or summarize -\ensuremath> translate. Recently, end-to-end models have achieved better results, but these approaches are mostly limited by their dependence on large-scale labeled data. We propose a solution based on mixed-lingual pre-training that leverages both cross-lingual tasks such as translation and monolingual tasks like masked language models. Thus, our model can leverage the massive monolingual data to enhance its modeling of language. Moreover, the architecture has no task-specific components, which saves memory and increases optimization efficiency. We show in experiments that this pre-training scheme can effectively boost the performance of cross-lingual summarization. In NCLS dataset, our model achieves an improvement of 2.82 (English to Chinese) and 1.15 (Chinese to English) ROUGE-1 scores over state-of-the-art results.
%R 10.18653/v1/2020.aacl-main.53
%U https://aclanthology.org/2020.aacl-main.53/
%U https://doi.org/10.18653/v1/2020.aacl-main.53
%P 536-541
Markdown (Informal)
[Mixed-Lingual Pre-training for Cross-lingual Summarization](https://aclanthology.org/2020.aacl-main.53/) (Xu et al., AACL 2020)
ACL
- Ruochen Xu, Chenguang Zhu, Yu Shi, Michael Zeng, and Xuedong Huang. 2020. Mixed-Lingual Pre-training for Cross-lingual Summarization. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 536–541, Suzhou, China. Association for Computational Linguistics.