@inproceedings{yang-etal-2019-paws,
title = "{PAWS}-{X}: A Cross-lingual Adversarial Dataset for Paraphrase Identification",
author = "Yang, Yinfei and
Zhang, Yuan and
Tar, Chris and
Baldridge, Jason",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1382",
doi = "10.18653/v1/D19-1382",
pages = "3687--3692",
abstract = "Most existing work on adversarial data generation focuses on English. For example, PAWS (Paraphrase Adversaries from Word Scrambling) consists of challenging English paraphrase identification pairs from Wikipedia and Quora. We remedy this gap with PAWS-X, a new dataset of 23,659 human translated PAWS evaluation pairs in six typologically distinct languages: French, Spanish, German, Chinese, Japanese, and Korean. We provide baseline numbers for three models with different capacity to capture non-local context and sentence structure, and using different multilingual training and evaluation regimes. Multilingual BERT fine-tuned on PAWS English plus machine-translated data performs the best, with a range of 83.1-90.8 accuracy across the non-English languages and an average accuracy gain of 23{\%} over the next best model. PAWS-X shows the effectiveness of deep, multilingual pre-training while also leaving considerable headroom as a new challenge to drive multilingual research that better captures structure and contextual information.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2019-paws">
<titleInfo>
<title>PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinfei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Tar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Baldridge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most existing work on adversarial data generation focuses on English. For example, PAWS (Paraphrase Adversaries from Word Scrambling) consists of challenging English paraphrase identification pairs from Wikipedia and Quora. We remedy this gap with PAWS-X, a new dataset of 23,659 human translated PAWS evaluation pairs in six typologically distinct languages: French, Spanish, German, Chinese, Japanese, and Korean. We provide baseline numbers for three models with different capacity to capture non-local context and sentence structure, and using different multilingual training and evaluation regimes. Multilingual BERT fine-tuned on PAWS English plus machine-translated data performs the best, with a range of 83.1-90.8 accuracy across the non-English languages and an average accuracy gain of 23% over the next best model. PAWS-X shows the effectiveness of deep, multilingual pre-training while also leaving considerable headroom as a new challenge to drive multilingual research that better captures structure and contextual information.</abstract>
<identifier type="citekey">yang-etal-2019-paws</identifier>
<identifier type="doi">10.18653/v1/D19-1382</identifier>
<location>
<url>https://aclanthology.org/D19-1382</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>3687</start>
<end>3692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification
%A Yang, Yinfei
%A Zhang, Yuan
%A Tar, Chris
%A Baldridge, Jason
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F yang-etal-2019-paws
%X Most existing work on adversarial data generation focuses on English. For example, PAWS (Paraphrase Adversaries from Word Scrambling) consists of challenging English paraphrase identification pairs from Wikipedia and Quora. We remedy this gap with PAWS-X, a new dataset of 23,659 human translated PAWS evaluation pairs in six typologically distinct languages: French, Spanish, German, Chinese, Japanese, and Korean. We provide baseline numbers for three models with different capacity to capture non-local context and sentence structure, and using different multilingual training and evaluation regimes. Multilingual BERT fine-tuned on PAWS English plus machine-translated data performs the best, with a range of 83.1-90.8 accuracy across the non-English languages and an average accuracy gain of 23% over the next best model. PAWS-X shows the effectiveness of deep, multilingual pre-training while also leaving considerable headroom as a new challenge to drive multilingual research that better captures structure and contextual information.
%R 10.18653/v1/D19-1382
%U https://aclanthology.org/D19-1382
%U https://doi.org/10.18653/v1/D19-1382
%P 3687-3692
Markdown (Informal)
[PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification](https://aclanthology.org/D19-1382) (Yang et al., EMNLP-IJCNLP 2019)
ACL
- Yinfei Yang, Yuan Zhang, Chris Tar, and Jason Baldridge. 2019. PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3687–3692, Hong Kong, China. Association for Computational Linguistics.