Learning Implicit Text Generation via Feature Matching

Inkit Padhi, Pierre Dognin, Ke Bai, Cícero Nogueira dos Santos, Vijil Chenthamarakshan, Youssef Mroueh, Payel Das


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.
Anthology ID:
2020.acl-main.354
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3855–3863
Language:
URL:
https://aclanthology.org/2020.acl-main.354
DOI:
10.18653/v1/2020.acl-main.354
Bibkey:
Cite (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.
Cite (Informal):
Learning Implicit Text Generation via Feature Matching (Padhi et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2020.acl-main.354.pdf
Video:
 http://slideslive.com/38929180
Data
MS COCO