@inproceedings{kajiwara-2019-negative,
title = "Negative Lexically Constrained Decoding for Paraphrase Generation",
author = "Kajiwara, Tomoyuki",
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/P19-1607",
doi = "10.18653/v1/P19-1607",
pages = "6047--6052",
abstract = "Paraphrase generation can be regarded as monolingual translation. Unlike bilingual machine translation, paraphrase generation rewrites only a limited portion of an input sentence. Hence, previous methods based on machine translation often perform conservatively to fail to make necessary rewrites. To solve this problem, we propose a neural model for paraphrase generation that first identifies words in the source sentence that should be paraphrased. Then, these words are paraphrased by the negative lexically constrained decoding that avoids outputting these words as they are. Experiments on text simplification and formality transfer show that our model improves the quality of paraphrasing by making necessary rewrites to an input sentence.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kajiwara-2019-negative">
<titleInfo>
<title>Negative Lexically Constrained Decoding for Paraphrase Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomoyuki</namePart>
<namePart type="family">Kajiwara</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>Paraphrase generation can be regarded as monolingual translation. Unlike bilingual machine translation, paraphrase generation rewrites only a limited portion of an input sentence. Hence, previous methods based on machine translation often perform conservatively to fail to make necessary rewrites. To solve this problem, we propose a neural model for paraphrase generation that first identifies words in the source sentence that should be paraphrased. Then, these words are paraphrased by the negative lexically constrained decoding that avoids outputting these words as they are. Experiments on text simplification and formality transfer show that our model improves the quality of paraphrasing by making necessary rewrites to an input sentence.</abstract>
<identifier type="citekey">kajiwara-2019-negative</identifier>
<identifier type="doi">10.18653/v1/P19-1607</identifier>
<location>
<url>https://aclanthology.org/P19-1607</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>6047</start>
<end>6052</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Negative Lexically Constrained Decoding for Paraphrase Generation
%A Kajiwara, Tomoyuki
%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 kajiwara-2019-negative
%X Paraphrase generation can be regarded as monolingual translation. Unlike bilingual machine translation, paraphrase generation rewrites only a limited portion of an input sentence. Hence, previous methods based on machine translation often perform conservatively to fail to make necessary rewrites. To solve this problem, we propose a neural model for paraphrase generation that first identifies words in the source sentence that should be paraphrased. Then, these words are paraphrased by the negative lexically constrained decoding that avoids outputting these words as they are. Experiments on text simplification and formality transfer show that our model improves the quality of paraphrasing by making necessary rewrites to an input sentence.
%R 10.18653/v1/P19-1607
%U https://aclanthology.org/P19-1607
%U https://doi.org/10.18653/v1/P19-1607
%P 6047-6052
Markdown (Informal)
[Negative Lexically Constrained Decoding for Paraphrase Generation](https://aclanthology.org/P19-1607) (Kajiwara, ACL 2019)
ACL