@inproceedings{roy-grangier-2019-unsupervised,
title = "Unsupervised Paraphrasing without Translation",
author = "Roy, Aurko and
Grangier, David",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1605",
doi = "10.18653/v1/P19-1605",
pages = "6033--6039",
abstract = "Paraphrasing is an important task demonstrating the ability to abstract semantic content from its surface form. Recent literature on automatic paraphrasing is dominated by methods leveraging machine translation as an intermediate step. This contrasts with humans, who can paraphrase without necessarily being bilingual. This work proposes to learn paraphrasing models only from a monolingual corpus. To that end, we propose a residual variant of vector-quantized variational auto-encoder. Our experiments consider paraphrase identification, and paraphrasing for training set augmentation, comparing to supervised and unsupervised translation-based approaches. Monolingual paraphrasing is shown to outperform unsupervised translation in all contexts. The comparison with supervised MT is more mixed: monolingual paraphrasing is interesting for identification and augmentation but supervised MT is superior for generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-grangier-2019-unsupervised">
<titleInfo>
<title>Unsupervised Paraphrasing without Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aurko</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Grangier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paraphrasing is an important task demonstrating the ability to abstract semantic content from its surface form. Recent literature on automatic paraphrasing is dominated by methods leveraging machine translation as an intermediate step. This contrasts with humans, who can paraphrase without necessarily being bilingual. This work proposes to learn paraphrasing models only from a monolingual corpus. To that end, we propose a residual variant of vector-quantized variational auto-encoder. Our experiments consider paraphrase identification, and paraphrasing for training set augmentation, comparing to supervised and unsupervised translation-based approaches. Monolingual paraphrasing is shown to outperform unsupervised translation in all contexts. The comparison with supervised MT is more mixed: monolingual paraphrasing is interesting for identification and augmentation but supervised MT is superior for generation.</abstract>
<identifier type="citekey">roy-grangier-2019-unsupervised</identifier>
<identifier type="doi">10.18653/v1/P19-1605</identifier>
<location>
<url>https://aclanthology.org/P19-1605</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>6033</start>
<end>6039</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unsupervised Paraphrasing without Translation
%A Roy, Aurko
%A Grangier, David
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F roy-grangier-2019-unsupervised
%X Paraphrasing is an important task demonstrating the ability to abstract semantic content from its surface form. Recent literature on automatic paraphrasing is dominated by methods leveraging machine translation as an intermediate step. This contrasts with humans, who can paraphrase without necessarily being bilingual. This work proposes to learn paraphrasing models only from a monolingual corpus. To that end, we propose a residual variant of vector-quantized variational auto-encoder. Our experiments consider paraphrase identification, and paraphrasing for training set augmentation, comparing to supervised and unsupervised translation-based approaches. Monolingual paraphrasing is shown to outperform unsupervised translation in all contexts. The comparison with supervised MT is more mixed: monolingual paraphrasing is interesting for identification and augmentation but supervised MT is superior for generation.
%R 10.18653/v1/P19-1605
%U https://aclanthology.org/P19-1605
%U https://doi.org/10.18653/v1/P19-1605
%P 6033-6039
Markdown (Informal)
[Unsupervised Paraphrasing without Translation](https://aclanthology.org/P19-1605) (Roy & Grangier, ACL 2019)
ACL
- Aurko Roy and David Grangier. 2019. Unsupervised Paraphrasing without Translation. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 6033–6039, Florence, Italy. Association for Computational Linguistics.