@inproceedings{nomoto-2019-generating,
title = "Generating Paraphrases with Lean Vocabulary",
author = "Nomoto, Tadashi",
editor = "van Deemter, Kees and
Lin, Chenghua and
Takamura, Hiroya",
booktitle = "Proceedings of the 12th International Conference on Natural Language Generation",
month = oct # "{--}" # nov,
year = "2019",
address = "Tokyo, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-8655",
doi = "10.18653/v1/W19-8655",
pages = "438--442",
abstract = "In this work, we examine whether it is possible to achieve the state of the art performance in paraphrase generation with reduced vocabulary. Our approach consists of building a convolution to sequence model (Conv2Seq) partially guided by the reinforcement learning, and training it on the subword representation of the input. The experiment on the Quora dataset, which contains over 140,000 pairs of sentences and corresponding paraphrases, found that with less than 1,000 token types, we were able to achieve performance which exceeded that of the current state of the art.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nomoto-2019-generating">
<titleInfo>
<title>Generating Paraphrases with Lean Vocabulary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tadashi</namePart>
<namePart type="family">Nomoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-oct–nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kees</namePart>
<namePart type="family">van Deemter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenghua</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Tokyo, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work, we examine whether it is possible to achieve the state of the art performance in paraphrase generation with reduced vocabulary. Our approach consists of building a convolution to sequence model (Conv2Seq) partially guided by the reinforcement learning, and training it on the subword representation of the input. The experiment on the Quora dataset, which contains over 140,000 pairs of sentences and corresponding paraphrases, found that with less than 1,000 token types, we were able to achieve performance which exceeded that of the current state of the art.</abstract>
<identifier type="citekey">nomoto-2019-generating</identifier>
<identifier type="doi">10.18653/v1/W19-8655</identifier>
<location>
<url>https://aclanthology.org/W19-8655</url>
</location>
<part>
<date>2019-oct–nov</date>
<extent unit="page">
<start>438</start>
<end>442</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating Paraphrases with Lean Vocabulary
%A Nomoto, Tadashi
%Y van Deemter, Kees
%Y Lin, Chenghua
%Y Takamura, Hiroya
%S Proceedings of the 12th International Conference on Natural Language Generation
%D 2019
%8 oct–nov
%I Association for Computational Linguistics
%C Tokyo, Japan
%F nomoto-2019-generating
%X In this work, we examine whether it is possible to achieve the state of the art performance in paraphrase generation with reduced vocabulary. Our approach consists of building a convolution to sequence model (Conv2Seq) partially guided by the reinforcement learning, and training it on the subword representation of the input. The experiment on the Quora dataset, which contains over 140,000 pairs of sentences and corresponding paraphrases, found that with less than 1,000 token types, we were able to achieve performance which exceeded that of the current state of the art.
%R 10.18653/v1/W19-8655
%U https://aclanthology.org/W19-8655
%U https://doi.org/10.18653/v1/W19-8655
%P 438-442
Markdown (Informal)
[Generating Paraphrases with Lean Vocabulary](https://aclanthology.org/W19-8655) (Nomoto, INLG 2019)
ACL
- Tadashi Nomoto. 2019. Generating Paraphrases with Lean Vocabulary. In Proceedings of the 12th International Conference on Natural Language Generation, pages 438–442, Tokyo, Japan. Association for Computational Linguistics.