Exploration of Numerical Precision in Deep Neural Networks

no code implementations • 3 May 2018 • Zhaoqi Li, Yu Ma, Catalina Vajiac, Yunkai Zhang

Reduced numerical precision is a common technique to reduce computational cost in many Deep Neural Networks (DNNs).

TabFact: A Large-scale Dataset for Table-based Fact Verification

1 code implementation • ICLR 2020 • Wenhu Chen, Hongmin Wang, Jianshu Chen, Yunkai Zhang, Hong Wang, Shiyang Li, Xiyou Zhou, William Yang Wang

To this end, we construct a large-scale dataset called TabFact with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED.

16k Fact Checking +4

You May Not Need Order in Time Series Forecasting

no code implementations • 21 Oct 2019 • Yunkai Zhang, Qiao Jiang, Shurui Li, Xiaoyong Jin, Xueying Ma, Xifeng Yan

Time series forecasting with limited data is a challenging yet critical task.

Time Series Time Series Forecasting

Logic2Text: High-Fidelity Natural Language Generation from Logical Forms

1 code implementation • Findings of the Association for Computational Linguistics 2020 • Zhiyu Chen, Wenhu Chen, Hanwen Zha, Xiyou Zhou, Yunkai Zhang, Sairam Sundaresan, William Yang Wang

If only provided with the table, it is hard for existing models to produce controllable and high-fidelity logical generations.

Text Generation Vocal Bursts Intensity Prediction

Continuous Conditional Generative Adversarial Networks (cGAN) with Generator Regularization

no code implementations • 27 Mar 2021 • Yufeng Zheng, Yunkai Zhang, Zeyu Zheng

To partially alleviate this difficulty, we propose a simple generator regularization term on the GAN generator loss in the form of Lipschitz penalty.