Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers

no code implementations • 22 May 2024 • Xin Cheng, Xiuying Chen, Shuqi Li, Di Luo, Xun Wang, Dongyan Zhao, Rui Yan

A vertical slicing of this grid combines the variates at each time step into a \textit{time token}, while a horizontal slicing embeds the individual series across all time steps into a \textit{variate token}.

Time Series Time Series Forecasting +1

Selecting Query-bag as Pseudo Relevance Feedback for Information-seeking Conversations

no code implementations • 22 Mar 2024 • Xiaoqing Zhang, Xiuying Chen, Shen Gao, Shuqi Li, Xin Gao, Ji-Rong Wen, Rui Yan

Given the user query, the information-seeking dialogue systems first retrieve a subset of response candidates, then further select the best response from the candidate set through re-ranking.

Contrastive Learning Re-Ranking