latent-GLAT: Glancing at Latent Variables for Parallel Text Generation

Yu Bao, Hao Zhou, Shujian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, Lei Li


Abstract
Recently, parallel text generation has received widespread attention due to its success in generation efficiency. Although many advanced techniques are proposed to improve its generation quality, they still need the help of an autoregressive model for training to overcome the one-to-many multi-modal phenomenon in the dataset, limiting their applications. In this paper, we propose GLAT, which employs the discrete latent variables to capture word categorical information and invoke an advanced curriculum learning technique, alleviating the multi-modality problem. Experiment results show that our method outperforms strong baselines without the help of an autoregressive model, which further broadens the application scenarios of the parallel decoding paradigm.
Anthology ID:
2022.acl-long.575
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8398–8409
Language:
URL:
https://aclanthology.org/2022.acl-long.575
DOI:
10.18653/v1/2022.acl-long.575
Bibkey:
Cite (ACL):
Yu Bao, Hao Zhou, Shujian Huang, Dongqi Wang, Lihua Qian, Xinyu Dai, Jiajun Chen, and Lei Li. 2022. latent-GLAT: Glancing at Latent Variables for Parallel Text Generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8398–8409, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
latent-GLAT: Glancing at Latent Variables for Parallel Text Generation (Bao et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.575.pdf
Code
 baoy-nlp/latent-glat
Data
DailyDialog