@inproceedings{hao-etal-2022-parazh,
title = "{P}ara{Z}h-22{M}: A Large-Scale {C}hinese Parabank via Machine Translation",
author = "Hao, Wenjie and
Xu, Hongfei and
Xiong, Deyi and
Zan, Hongying and
Mu, Lingling",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.341",
pages = "3885--3897",
abstract = "Paraphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. (2019b) propose to extract sentence-level paraphrases from multiple Chinese translations of the same source texts, and construct the PKU Paraphrase Bank of 0.5M sentence pairs. However, despite being the largest Chinese parabank to date, the size of PKU parabank is limited by the availability of one-to-many sentence translation data, and cannot well support the training of large Chinese paraphrasers. In this paper, we relieve the restriction with one-to-many sentence translation data, and construct ParaZh-22M, a larger Chinese parabank that is composed of 22M sentence pairs, based on one-to-one bilingual sentence translation data and machine translation (MT). In our data augmentation experiments, we show that paraphrasing based on ParaZh-22M can bring about consistent and significant improvements over several strong baselines on a wide range of Chinese NLP tasks, including a number of Chinese natural language understanding benchmarks (CLUE) and low-resource machine translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hao-etal-2022-parazh">
<titleInfo>
<title>ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongying</namePart>
<namePart type="family">Zan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingling</namePart>
<namePart type="family">Mu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paraphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. (2019b) propose to extract sentence-level paraphrases from multiple Chinese translations of the same source texts, and construct the PKU Paraphrase Bank of 0.5M sentence pairs. However, despite being the largest Chinese parabank to date, the size of PKU parabank is limited by the availability of one-to-many sentence translation data, and cannot well support the training of large Chinese paraphrasers. In this paper, we relieve the restriction with one-to-many sentence translation data, and construct ParaZh-22M, a larger Chinese parabank that is composed of 22M sentence pairs, based on one-to-one bilingual sentence translation data and machine translation (MT). In our data augmentation experiments, we show that paraphrasing based on ParaZh-22M can bring about consistent and significant improvements over several strong baselines on a wide range of Chinese NLP tasks, including a number of Chinese natural language understanding benchmarks (CLUE) and low-resource machine translation.</abstract>
<identifier type="citekey">hao-etal-2022-parazh</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.341</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>3885</start>
<end>3897</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation
%A Hao, Wenjie
%A Xu, Hongfei
%A Xiong, Deyi
%A Zan, Hongying
%A Mu, Lingling
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F hao-etal-2022-parazh
%X Paraphrasing, i.e., restating the same meaning in different ways, is an important data augmentation approach for natural language processing (NLP). Zhang et al. (2019b) propose to extract sentence-level paraphrases from multiple Chinese translations of the same source texts, and construct the PKU Paraphrase Bank of 0.5M sentence pairs. However, despite being the largest Chinese parabank to date, the size of PKU parabank is limited by the availability of one-to-many sentence translation data, and cannot well support the training of large Chinese paraphrasers. In this paper, we relieve the restriction with one-to-many sentence translation data, and construct ParaZh-22M, a larger Chinese parabank that is composed of 22M sentence pairs, based on one-to-one bilingual sentence translation data and machine translation (MT). In our data augmentation experiments, we show that paraphrasing based on ParaZh-22M can bring about consistent and significant improvements over several strong baselines on a wide range of Chinese NLP tasks, including a number of Chinese natural language understanding benchmarks (CLUE) and low-resource machine translation.
%U https://aclanthology.org/2022.coling-1.341
%P 3885-3897
Markdown (Informal)
[ParaZh-22M: A Large-Scale Chinese Parabank via Machine Translation](https://aclanthology.org/2022.coling-1.341) (Hao et al., COLING 2022)
ACL