Implicit Deep Latent Variable Models for Text Generation

Le Fang, Chunyuan Li, Jianfeng Gao, Wen Dong, Changyou Chen

[How to correct problems with metadata yourself]

Abstract
Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the representation power of VAEs is limited due to two reasons: (1) the Gaussian assumption is often made on the variational posteriors; and meanwhile (2) a notorious “posterior collapse” issue occurs. In this paper, we advocate sample-based representations of variational distributions for natural language, leading to implicit latent features, which can provide flexible representation power compared with Gaussian-based posteriors. We further develop an LVM to directly match the aggregated posterior to the prior. It can be viewed as a natural extension of VAEs with a regularization of maximizing mutual information, mitigating the “posterior collapse” issue. We demonstrate the effectiveness and versatility of our models in various text generation scenarios, including language modeling, unaligned style transfer, and dialog response generation. The source code to reproduce our experimental results is available on GitHub.
Anthology ID:
D19-1407
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3946–3956
Language:
URL:
https://aclanthology.org/D19-1407
DOI:
10.18653/v1/D19-1407
Bibkey:
Cite (ACL):
Le Fang, Chunyuan Li, Jianfeng Gao, Wen Dong, and Changyou Chen. 2019. Implicit Deep Latent Variable Models for Text Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3946–3956, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Implicit Deep Latent Variable Models for Text Generation (Fang et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/teach-a-man-to-fish/D19-1407.pdf
Attachment:
 D19-1407.Attachment.zip
Code
 fangleai/Implicit-LVM
Data
DailyDialog
PDF Search Code Attachment