@inproceedings{kazemnejad-etal-2020-paraphrase,
title = "Paraphrase Generation by Learning How to Edit from Samples",
author = "Kazemnejad, Amirhossein and
Salehi, Mohammadreza and
Soleymani Baghshah, Mahdieh",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.535",
doi = "10.18653/v1/2020.acl-main.535",
pages = "6010--6021",
abstract = "Neural sequence to sequence text generation has been proved to be a viable approach to paraphrase generation. Despite promising results, paraphrases generated by these models mostly suffer from lack of quality and diversity. To address these problems, we propose a novel retrieval-based method for paraphrase generation. Our model first retrieves a paraphrase pair similar to the input sentence from a pre-defined index. With its novel editor module, the model then paraphrases the input sequence by editing it using the extracted relations between the retrieved pair of sentences. In order to have fine-grained control over the editing process, our model uses the newly introduced concept of Micro Edit Vectors. It both extracts and exploits these vectors using the attention mechanism in the Transformer architecture. Experimental results show the superiority of our paraphrase generation method in terms of both automatic metrics, and human evaluation of relevance, grammaticality, and diversity of generated paraphrases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kazemnejad-etal-2020-paraphrase">
<titleInfo>
<title>Paraphrase Generation by Learning How to Edit from Samples</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amirhossein</namePart>
<namePart type="family">Kazemnejad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammadreza</namePart>
<namePart type="family">Salehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahdieh</namePart>
<namePart type="family">Soleymani Baghshah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural sequence to sequence text generation has been proved to be a viable approach to paraphrase generation. Despite promising results, paraphrases generated by these models mostly suffer from lack of quality and diversity. To address these problems, we propose a novel retrieval-based method for paraphrase generation. Our model first retrieves a paraphrase pair similar to the input sentence from a pre-defined index. With its novel editor module, the model then paraphrases the input sequence by editing it using the extracted relations between the retrieved pair of sentences. In order to have fine-grained control over the editing process, our model uses the newly introduced concept of Micro Edit Vectors. It both extracts and exploits these vectors using the attention mechanism in the Transformer architecture. Experimental results show the superiority of our paraphrase generation method in terms of both automatic metrics, and human evaluation of relevance, grammaticality, and diversity of generated paraphrases.</abstract>
<identifier type="citekey">kazemnejad-etal-2020-paraphrase</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.535</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.535</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>6010</start>
<end>6021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paraphrase Generation by Learning How to Edit from Samples
%A Kazemnejad, Amirhossein
%A Salehi, Mohammadreza
%A Soleymani Baghshah, Mahdieh
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F kazemnejad-etal-2020-paraphrase
%X Neural sequence to sequence text generation has been proved to be a viable approach to paraphrase generation. Despite promising results, paraphrases generated by these models mostly suffer from lack of quality and diversity. To address these problems, we propose a novel retrieval-based method for paraphrase generation. Our model first retrieves a paraphrase pair similar to the input sentence from a pre-defined index. With its novel editor module, the model then paraphrases the input sequence by editing it using the extracted relations between the retrieved pair of sentences. In order to have fine-grained control over the editing process, our model uses the newly introduced concept of Micro Edit Vectors. It both extracts and exploits these vectors using the attention mechanism in the Transformer architecture. Experimental results show the superiority of our paraphrase generation method in terms of both automatic metrics, and human evaluation of relevance, grammaticality, and diversity of generated paraphrases.
%R 10.18653/v1/2020.acl-main.535
%U https://aclanthology.org/2020.acl-main.535
%U https://doi.org/10.18653/v1/2020.acl-main.535
%P 6010-6021
Markdown (Informal)
[Paraphrase Generation by Learning How to Edit from Samples](https://aclanthology.org/2020.acl-main.535) (Kazemnejad et al., ACL 2020)
ACL
- Amirhossein Kazemnejad, Mohammadreza Salehi, and Mahdieh Soleymani Baghshah. 2020. Paraphrase Generation by Learning How to Edit from Samples. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6010–6021, Online. Association for Computational Linguistics.