@inproceedings{xue-etal-2023-unifying,
title = "Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation",
author = "Xue, Mingfeng and
Liu, Dayiheng and
Lei, Wenqiang and
Fu, Jie and
Lan, Jian and
Li, Mei and
Yang, Baosong and
Xie, Jun and
Zhang, Yidan and
Peng, Dezhong and
Lv, Jiancheng",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.852",
doi = "10.18653/v1/2023.emnlp-main.852",
pages = "13805--13822",
abstract = "Unsupervised paraphrase generation is a challenging task that benefits a variety of downstream NLP applications. Current unsupervised methods for paraphrase generation typically employ round-trip translation or denoising, which require translation corpus and result in paraphrases overly similar to the original sentences in surface structure. Most of these methods lack explicit control over the similarity between the original and generated sentences, and the entities are also less correctly kept. To obviate the reliance on translation data and prompt greater variations in surface structure, we propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence. To control the similarity and generate accurate entities, we propose an unsupervised paraphrasing model that encodes the sentence meaning and the entities with discrete and continuous variables, respectively. The similarity can be controlled by sampling discrete variables and the entities are kept substantially accurate due to the specific modeling of entities using continuous variables. Experimental results on two benchmark datasets demonstrate the advantages of our pseudo-data construction method compared to round-trip translation, and the superiority of our paraphrasing model over the state-of-the-art unsupervised methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xue-etal-2023-unifying">
<titleInfo>
<title>Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingfeng</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayiheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqiang</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baosong</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yidan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dezhong</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiancheng</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unsupervised paraphrase generation is a challenging task that benefits a variety of downstream NLP applications. Current unsupervised methods for paraphrase generation typically employ round-trip translation or denoising, which require translation corpus and result in paraphrases overly similar to the original sentences in surface structure. Most of these methods lack explicit control over the similarity between the original and generated sentences, and the entities are also less correctly kept. To obviate the reliance on translation data and prompt greater variations in surface structure, we propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence. To control the similarity and generate accurate entities, we propose an unsupervised paraphrasing model that encodes the sentence meaning and the entities with discrete and continuous variables, respectively. The similarity can be controlled by sampling discrete variables and the entities are kept substantially accurate due to the specific modeling of entities using continuous variables. Experimental results on two benchmark datasets demonstrate the advantages of our pseudo-data construction method compared to round-trip translation, and the superiority of our paraphrasing model over the state-of-the-art unsupervised methods.</abstract>
<identifier type="citekey">xue-etal-2023-unifying</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.852</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.852</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13805</start>
<end>13822</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation
%A Xue, Mingfeng
%A Liu, Dayiheng
%A Lei, Wenqiang
%A Fu, Jie
%A Lan, Jian
%A Li, Mei
%A Yang, Baosong
%A Xie, Jun
%A Zhang, Yidan
%A Peng, Dezhong
%A Lv, Jiancheng
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F xue-etal-2023-unifying
%X Unsupervised paraphrase generation is a challenging task that benefits a variety of downstream NLP applications. Current unsupervised methods for paraphrase generation typically employ round-trip translation or denoising, which require translation corpus and result in paraphrases overly similar to the original sentences in surface structure. Most of these methods lack explicit control over the similarity between the original and generated sentences, and the entities are also less correctly kept. To obviate the reliance on translation data and prompt greater variations in surface structure, we propose a self-supervised pseudo-data construction method that generates diverse pseudo-paraphrases in distinct surface structures for a given sentence. To control the similarity and generate accurate entities, we propose an unsupervised paraphrasing model that encodes the sentence meaning and the entities with discrete and continuous variables, respectively. The similarity can be controlled by sampling discrete variables and the entities are kept substantially accurate due to the specific modeling of entities using continuous variables. Experimental results on two benchmark datasets demonstrate the advantages of our pseudo-data construction method compared to round-trip translation, and the superiority of our paraphrasing model over the state-of-the-art unsupervised methods.
%R 10.18653/v1/2023.emnlp-main.852
%U https://aclanthology.org/2023.emnlp-main.852
%U https://doi.org/10.18653/v1/2023.emnlp-main.852
%P 13805-13822
Markdown (Informal)
[Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation](https://aclanthology.org/2023.emnlp-main.852) (Xue et al., EMNLP 2023)
ACL
- Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Jie Fu, Jian Lan, Mei Li, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, and Jiancheng Lv. 2023. Unifying Discrete and Continuous Representations for Unsupervised Paraphrase Generation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13805–13822, Singapore. Association for Computational Linguistics.