@inproceedings{cai-etal-2021-revisiting,
title = "Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot",
author = "Cai, Yitao and
Cao, Yue and
Wan, Xiaojun",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.350",
doi = "10.18653/v1/2021.emnlp-main.350",
pages = "4255--4268",
abstract = "Paraphrases refer to texts that convey the same meaning with different expression forms. Pivot-based methods, also known as the round-trip translation, have shown promising results in generating high-quality paraphrases. However, existing pivot-based methods all rely on language as the pivot, where large-scale, high-quality parallel bilingual texts are required. In this paper, we explore the feasibility of using semantic and syntactic representations as the pivot for paraphrase generation. Concretely, we transform a sentence into a variety of different semantic or syntactic representations (including AMR, UD, and latent semantic representation), and then decode the sentence back from the semantic representations. We further explore a pretraining-based approach to compress the pipeline process into an end-to-end framework. We conduct experiments comparing different approaches with different kinds of pivots. Experimental results show that taking AMR as pivot can obtain paraphrases with better quality than taking language as the pivot. The end-to-end framework can reduce semantic shift when language is used as the pivot. Besides, several unsupervised pivot-based methods can generate paraphrases with similar quality as the supervised sequence-to-sequence model, which indicates that parallel data of paraphrases may not be necessary for paraphrase generation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2021-revisiting">
<titleInfo>
<title>Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yitao</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paraphrases refer to texts that convey the same meaning with different expression forms. Pivot-based methods, also known as the round-trip translation, have shown promising results in generating high-quality paraphrases. However, existing pivot-based methods all rely on language as the pivot, where large-scale, high-quality parallel bilingual texts are required. In this paper, we explore the feasibility of using semantic and syntactic representations as the pivot for paraphrase generation. Concretely, we transform a sentence into a variety of different semantic or syntactic representations (including AMR, UD, and latent semantic representation), and then decode the sentence back from the semantic representations. We further explore a pretraining-based approach to compress the pipeline process into an end-to-end framework. We conduct experiments comparing different approaches with different kinds of pivots. Experimental results show that taking AMR as pivot can obtain paraphrases with better quality than taking language as the pivot. The end-to-end framework can reduce semantic shift when language is used as the pivot. Besides, several unsupervised pivot-based methods can generate paraphrases with similar quality as the supervised sequence-to-sequence model, which indicates that parallel data of paraphrases may not be necessary for paraphrase generation.</abstract>
<identifier type="citekey">cai-etal-2021-revisiting</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.350</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.350</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>4255</start>
<end>4268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot
%A Cai, Yitao
%A Cao, Yue
%A Wan, Xiaojun
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F cai-etal-2021-revisiting
%X Paraphrases refer to texts that convey the same meaning with different expression forms. Pivot-based methods, also known as the round-trip translation, have shown promising results in generating high-quality paraphrases. However, existing pivot-based methods all rely on language as the pivot, where large-scale, high-quality parallel bilingual texts are required. In this paper, we explore the feasibility of using semantic and syntactic representations as the pivot for paraphrase generation. Concretely, we transform a sentence into a variety of different semantic or syntactic representations (including AMR, UD, and latent semantic representation), and then decode the sentence back from the semantic representations. We further explore a pretraining-based approach to compress the pipeline process into an end-to-end framework. We conduct experiments comparing different approaches with different kinds of pivots. Experimental results show that taking AMR as pivot can obtain paraphrases with better quality than taking language as the pivot. The end-to-end framework can reduce semantic shift when language is used as the pivot. Besides, several unsupervised pivot-based methods can generate paraphrases with similar quality as the supervised sequence-to-sequence model, which indicates that parallel data of paraphrases may not be necessary for paraphrase generation.
%R 10.18653/v1/2021.emnlp-main.350
%U https://aclanthology.org/2021.emnlp-main.350
%U https://doi.org/10.18653/v1/2021.emnlp-main.350
%P 4255-4268
Markdown (Informal)
[Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot](https://aclanthology.org/2021.emnlp-main.350) (Cai et al., EMNLP 2021)
ACL