@inproceedings{padhi-etal-2020-learning,
title = "Learning Implicit Text Generation via Feature Matching",
author = "Padhi, Inkit and
Dognin, Pierre and
Bai, Ke and
Nogueira dos Santos, C{\'\i}cero and
Chenthamarakshan, Vijil and
Mroueh, Youssef and
Das, Payel",
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.354",
doi = "10.18653/v1/2020.acl-main.354",
pages = "3855--3863",
abstract = "Generative feature matching network (GFMN) is an approach for training state-of-the-art implicit generative models for images by performing moment matching on features from pre-trained neural networks. In this paper, we present new GFMN formulations that are effective for sequential data. Our experimental results show the effectiveness of the proposed method, SeqGFMN, for three distinct generation tasks in English: unconditional text generation, class-conditional text generation, and unsupervised text style transfer. SeqGFMN is stable to train and outperforms various adversarial approaches for text generation and text style transfer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="padhi-etal-2020-learning">
<titleInfo>
<title>Learning Implicit Text Generation via Feature Matching</title>
</titleInfo>
<name type="personal">
<namePart type="given">Inkit</namePart>
<namePart type="family">Padhi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Dognin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cícero</namePart>
<namePart type="family">Nogueira dos Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijil</namePart>
<namePart type="family">Chenthamarakshan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Mroueh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Payel</namePart>
<namePart type="family">Das</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>Generative feature matching network (GFMN) is an approach for training state-of-the-art implicit generative models for images by performing moment matching on features from pre-trained neural networks. In this paper, we present new GFMN formulations that are effective for sequential data. Our experimental results show the effectiveness of the proposed method, SeqGFMN, for three distinct generation tasks in English: unconditional text generation, class-conditional text generation, and unsupervised text style transfer. SeqGFMN is stable to train and outperforms various adversarial approaches for text generation and text style transfer.</abstract>
<identifier type="citekey">padhi-etal-2020-learning</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.354</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.354</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>3855</start>
<end>3863</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Implicit Text Generation via Feature Matching
%A Padhi, Inkit
%A Dognin, Pierre
%A Bai, Ke
%A Nogueira dos Santos, Cícero
%A Chenthamarakshan, Vijil
%A Mroueh, Youssef
%A Das, Payel
%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 padhi-etal-2020-learning
%X Generative feature matching network (GFMN) is an approach for training state-of-the-art implicit generative models for images by performing moment matching on features from pre-trained neural networks. In this paper, we present new GFMN formulations that are effective for sequential data. Our experimental results show the effectiveness of the proposed method, SeqGFMN, for three distinct generation tasks in English: unconditional text generation, class-conditional text generation, and unsupervised text style transfer. SeqGFMN is stable to train and outperforms various adversarial approaches for text generation and text style transfer.
%R 10.18653/v1/2020.acl-main.354
%U https://aclanthology.org/2020.acl-main.354
%U https://doi.org/10.18653/v1/2020.acl-main.354
%P 3855-3863
Markdown (Informal)
[Learning Implicit Text Generation via Feature Matching](https://aclanthology.org/2020.acl-main.354) (Padhi et al., ACL 2020)
ACL
- Inkit Padhi, Pierre Dognin, Ke Bai, Cícero Nogueira dos Santos, Vijil Chenthamarakshan, Youssef Mroueh, and Payel Das. 2020. Learning Implicit Text Generation via Feature Matching. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3855–3863, Online. Association for Computational Linguistics.