Data-dependent Gaussian Prior Objective for Language Generation

By Zuchao Li, Rui Wang, Kehai Chen, Masso Utiyama, Eiichiro Sumita, Zhuosheng Zhang, Hai Zhao. 2020

69 citations recorded by the source corpus.

Subfields: Natural Language Processing, Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

1. Tao Qin
2. Tie-Yan Liu
3. Xu Tan
4. Xian Li
5. Jiatao Gu
6. Yuqing Tang
7. Chau Tran
8. Sang-gil Lee

In Generative Models

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Heeseung Kim
5. Chaehun Shin
6. Sang-gil Lee
7. Xian Li
8. Chang Liu

Citations in the corpus

• Cross-lingual Retrieval for Iterative Self-Supervised Training (2020, background): “1 - D2GPO [33] 28.”
• PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Driven Adaptive Prior (2021, result): “…an informative prior distribution for deep generative model are not new, and there has been a variety of studies investigating a better prior, ranging from hand-crafted [21, 38], autoregressive [3], vector quantization [27], prior encoder [30], and data-dependent approaches similar to ours [19].”
• PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior (2021, result): “…investigating a better prior, ranging from hand-crafted (Nalisnick & Smyth, 2017; Tomczak & Welling, 2018), autoregressive (Chen et al., 2017), vector quantization (Razavi et al., 2019), prior encoder (Rezende & Mohamed, 2015), and data-dependent approaches similar to ours (Li et al., 2019).”