DGST: a Dual-Generator Network for Text Style Transfer

Xiao Li; Guanyi Chen; Chenghua Lin; Ruizhe Li

doi:10.18653/v1/2020.emnlp-main.578

DGST: a Dual-Generator Network for Text Style Transfer

Xiao Li, Guanyi Chen, Chenghua Lin, Ruizhe Li

Sub Natural Language Processing

University of Sheffield

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.

Original language	English
Title of host publication	Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Editors	Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Publisher	Association for Computational Linguistics
Pages	7131-7136
Number of pages	6
DOIs	https://doi.org/10.18653/v1/2020.emnlp-main.578
Publication status	Published - 15 Nov 2020
Event	Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) - Duration: 15 Nov 2020 → … https://2020.emnlp.org/

Conference

Conference	Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Period	15/11/20 → …
Internet address	https://2020.emnlp.org/

Access to Document

10.18653/v1/2020.emnlp-main.578

2020.emnlp-main.578Final published version, 296 KB

Cite this

@inproceedings{02926a883cbd4c708dc0ce2bea4c9502,

title = "DGST: a Dual-Generator Network for Text Style Transfer",

abstract = "We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.",

author = "Xiao Li and Guanyi Chen and Chenghua Lin and Ruizhe Li",

year = "2020",

month = nov,

day = "15",

doi = "10.18653/v1/2020.emnlp-main.578",

language = "English",

pages = "7131--7136",

editor = "Webber, {Bonnie } and Cohn, {Trevor } and He, {Yulan } and Liu, {Yang }",

booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",

publisher = "Association for Computational Linguistics",

address = "United States",

note = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) ; Conference date: 15-11-2020",

url = "https://2020.emnlp.org/",

}

Li, X, Chen, G, Lin, C & Li, R 2020, DGST: a Dual-Generator Network for Text Style Transfer. in B Webber, T Cohn, Y He & Y Liu (eds), Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, pp. 7131-7136, Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 15/11/20. https://doi.org/10.18653/v1/2020.emnlp-main.578

DGST: a Dual-Generator Network for Text Style Transfer. / Li, Xiao; Chen, Guanyi; Lin, Chenghua et al.
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). ed. / Bonnie Webber; Trevor Cohn; Yulan He; Yang Liu. Association for Computational Linguistics, 2020. p. 7131-7136.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - DGST: a Dual-Generator Network for Text Style Transfer

AU - Li, Xiao

AU - Chen, Guanyi

AU - Lin, Chenghua

AU - Li, Ruizhe

PY - 2020/11/15

Y1 - 2020/11/15

N2 - We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.

AB - We propose DGST, a novel and simple Dual-Generator network architecture for text Style Transfer. Our model employs two generators only, and does not rely on any discriminators or parallel corpus for training. Both quantitative and qualitative experiments on the Yelp and IMDb datasets show that our model gives competitive performance compared to several strong baselines with more complicated architecture designs.

U2 - 10.18653/v1/2020.emnlp-main.578

DO - 10.18653/v1/2020.emnlp-main.578

M3 - Conference contribution

SP - 7131

EP - 7136

BT - Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

A2 - Webber, Bonnie

A2 - Cohn, Trevor

A2 - He, Yulan

A2 - Liu, Yang

PB - Association for Computational Linguistics

T2 - Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Y2 - 15 November 2020

ER -

DGST: a Dual-Generator Network for Text Style Transfer

Abstract

Conference

Access to Document

Fingerprint

Cite this