Shiyang Li
University of California, Santa Barbara
26 Papers
171 Citations
Shiyang Li is an academic researcher from University of California, Santa Barbara. The author has contributed to research in topics: Computer science & Counterfactual thinking. The author has an hindex of 7, co-authored 12 publications.
Chat about Author
Papers
•Proceedings Article
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Shiyang Li,Xiaoyong Jin,Yao Xuan,Xiyou Zhou,Wenhu Chen,Yu-Xiang Wang,Xifeng Yan +6 more
- 29 Jun 2019
TL;DR: First, convolutional self-attention is proposed by producing queries and keys with causal convolution so that local context can be better incorporated into attention mechanism, and LogSparse Transformer is proposed, improving forecasting accuracy for time series with fine granularity and strong long-term dependencies under constrained memory budget.
•Posted Content
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting.
TL;DR: In this article, a convolutional self-attention with causal convolution was proposed to improve the accuracy of time series forecasting with fine granularity and strong long-term dependencies.
633
•Posted Content
TabFact: A Large-scale Dataset for Table-based Fact Verification
Wenhu Chen,Hongmin Wang,Jianshu Chen,Yunkai Zhang,Hong Wang,Shiyang Li,Xiyou Zhou,William Yang Wang +7 more
TL;DR: A large-scale dataset with 16k Wikipedia tables as the evidence for 118k human-annotated natural language statements, which are labeled as either ENTAILED or REFUTED is constructed and two different models are designed: Table-BERT and Latent Program Algorithm (LPA).
•Proceedings Article
TabFact: A Large-scale Dataset for Table-based Fact Verification
Wenhu Chen,Hongmin Wang,Jianshu Chen,Yunkai Zhang,Hong Wang,Shiyang Li,Xiyou Zhou,William Yang Wang +7 more
- 30 Apr 2020
TL;DR: Zhang et al. as mentioned in this paper designed two different models: Table-BERT and Latent Program Algorithm (LPA) to verify whether a textual hypothesis holds based on the given evidence, also known as fact verification.
•Proceedings Article
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
Shiyang Li,Semih Yavuz,Kazuma Hashimoto,Jia Li,Tong Niu,Nazneen Fatema Rajani,Xifeng Yan,Yingbo Zhou,Caiming Xiong +8 more
- 03 May 2021
TL;DR: Human evaluations show that CoCo-generated conversations perfectly reflect the underlying user goal with more than 95% accuracy and are as human-like as the original conversations, further strengthening its reliability and promise to be adopted as part of the robustness evaluation of DST models.