@inproceedings{yin-etal-2022-learning,
title = "Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning",
author = "Yin, Haiyan and
Li, Dingcheng and
Li, Ping",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.99",
doi = "10.18653/v1/2022.naacl-main.99",
pages = "1385--1395",
abstract = "Paraphrase generation is an important language generation task attempting to interpret user intents and systematically generate new phrases of identical meanings to the given ones. However, the effectiveness of paraphrase generation is constrained by the access to the golden labeled data pairs where both the amount and the quality of the training data pairs are restricted. In this paper, we propose a new weakly supervised paraphrase generation approach that extends the success of a recent work that leverages reinforcement learning for effective model training with data selection. While data selection is privileged for the target task which has noisy data, developing a reinforced selective learning regime faces several unresolved challenges. In this paper, we carry on important discussions about the above problem and present a new model that could partially overcome the discussed issues with a model-based planning feature and a reward normalization feature. We perform extensive evaluation on four weakly supervised paraphrase generation tasks where the results show that our method could significantly improve the state-of-the-art performance on the evaluation datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yin-etal-2022-learning">
<titleInfo>
<title>Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haiyan</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dingcheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Paraphrase generation is an important language generation task attempting to interpret user intents and systematically generate new phrases of identical meanings to the given ones. However, the effectiveness of paraphrase generation is constrained by the access to the golden labeled data pairs where both the amount and the quality of the training data pairs are restricted. In this paper, we propose a new weakly supervised paraphrase generation approach that extends the success of a recent work that leverages reinforcement learning for effective model training with data selection. While data selection is privileged for the target task which has noisy data, developing a reinforced selective learning regime faces several unresolved challenges. In this paper, we carry on important discussions about the above problem and present a new model that could partially overcome the discussed issues with a model-based planning feature and a reward normalization feature. We perform extensive evaluation on four weakly supervised paraphrase generation tasks where the results show that our method could significantly improve the state-of-the-art performance on the evaluation datasets.</abstract>
<identifier type="citekey">yin-etal-2022-learning</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.99</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.99</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1385</start>
<end>1395</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning
%A Yin, Haiyan
%A Li, Dingcheng
%A Li, Ping
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F yin-etal-2022-learning
%X Paraphrase generation is an important language generation task attempting to interpret user intents and systematically generate new phrases of identical meanings to the given ones. However, the effectiveness of paraphrase generation is constrained by the access to the golden labeled data pairs where both the amount and the quality of the training data pairs are restricted. In this paper, we propose a new weakly supervised paraphrase generation approach that extends the success of a recent work that leverages reinforcement learning for effective model training with data selection. While data selection is privileged for the target task which has noisy data, developing a reinforced selective learning regime faces several unresolved challenges. In this paper, we carry on important discussions about the above problem and present a new model that could partially overcome the discussed issues with a model-based planning feature and a reward normalization feature. We perform extensive evaluation on four weakly supervised paraphrase generation tasks where the results show that our method could significantly improve the state-of-the-art performance on the evaluation datasets.
%R 10.18653/v1/2022.naacl-main.99
%U https://aclanthology.org/2022.naacl-main.99
%U https://doi.org/10.18653/v1/2022.naacl-main.99
%P 1385-1395
Markdown (Informal)
[Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement Learning](https://aclanthology.org/2022.naacl-main.99) (Yin et al., NAACL 2022)
ACL