@inproceedings{yang-etal-2021-syntactically,
title = "Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data",
author = "Yang, Erguang and
Liu, Mingtong and
Xiong, Deyi and
Zhang, Yujie and
Meng, Yao and
Hu, Changjian and
Xu, Jinan and
Chen, Yufeng",
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.203",
doi = "10.18653/v1/2021.emnlp-main.203",
pages = "2594--2604",
abstract = "Previous works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this research direction to the extreme and investigate whether it is possible to learn syntactically controlled paraphrase generation with nonparallel data. We propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder (VAE) which can generate texts in a specified syntactic structure. Particularly, we design a two-stage learning method to effectively train the model using non-parallel data. The conditional VAE is trained to reconstruct the input sentence according to the given input and its syntactic structure. Furthermore, to improve the syntactic controllability and semantic consistency of the pre-trained conditional VAE, we fine-tune it using syntax controlling and cycle reconstruction learning objectives, and employ Gumbel-Softmax to combine these new learning objectives. Experiment results demonstrate that the proposed model trained only on non-parallel data is capable of generating diverse paraphrases with specified syntactic structure. Additionally, we validate the effectiveness of our method for generating syntactically adversarial examples on the sentiment analysis task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2021-syntactically">
<titleInfo>
<title>Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erguang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingtong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deyi</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujie</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Meng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changjian</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Chen</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>
<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>Previous works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this research direction to the extreme and investigate whether it is possible to learn syntactically controlled paraphrase generation with nonparallel data. We propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder (VAE) which can generate texts in a specified syntactic structure. Particularly, we design a two-stage learning method to effectively train the model using non-parallel data. The conditional VAE is trained to reconstruct the input sentence according to the given input and its syntactic structure. Furthermore, to improve the syntactic controllability and semantic consistency of the pre-trained conditional VAE, we fine-tune it using syntax controlling and cycle reconstruction learning objectives, and employ Gumbel-Softmax to combine these new learning objectives. Experiment results demonstrate that the proposed model trained only on non-parallel data is capable of generating diverse paraphrases with specified syntactic structure. Additionally, we validate the effectiveness of our method for generating syntactically adversarial examples on the sentiment analysis task.</abstract>
<identifier type="citekey">yang-etal-2021-syntactically</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.203</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.203</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2594</start>
<end>2604</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data
%A Yang, Erguang
%A Liu, Mingtong
%A Xiong, Deyi
%A Zhang, Yujie
%A Meng, Yao
%A Hu, Changjian
%A Xu, Jinan
%A Chen, Yufeng
%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 yang-etal-2021-syntactically
%X Previous works on syntactically controlled paraphrase generation heavily rely on large-scale parallel paraphrase data that is not easily available for many languages and domains. In this paper, we take this research direction to the extreme and investigate whether it is possible to learn syntactically controlled paraphrase generation with nonparallel data. We propose a syntactically-informed unsupervised paraphrasing model based on conditional variational auto-encoder (VAE) which can generate texts in a specified syntactic structure. Particularly, we design a two-stage learning method to effectively train the model using non-parallel data. The conditional VAE is trained to reconstruct the input sentence according to the given input and its syntactic structure. Furthermore, to improve the syntactic controllability and semantic consistency of the pre-trained conditional VAE, we fine-tune it using syntax controlling and cycle reconstruction learning objectives, and employ Gumbel-Softmax to combine these new learning objectives. Experiment results demonstrate that the proposed model trained only on non-parallel data is capable of generating diverse paraphrases with specified syntactic structure. Additionally, we validate the effectiveness of our method for generating syntactically adversarial examples on the sentiment analysis task.
%R 10.18653/v1/2021.emnlp-main.203
%U https://aclanthology.org/2021.emnlp-main.203
%U https://doi.org/10.18653/v1/2021.emnlp-main.203
%P 2594-2604
Markdown (Informal)
[Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data](https://aclanthology.org/2021.emnlp-main.203) (Yang et al., EMNLP 2021)
ACL
- Erguang Yang, Mingtong Liu, Deyi Xiong, Yujie Zhang, Yao Meng, Changjian Hu, Jinan Xu, and Yufeng Chen. 2021. Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel Data. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 2594–2604, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.