Bridging the Gap Between Training and Inference for Spatio-Temporal Forecasting

no code implementations • 19 May 2020 • Hong-Bin Liu, Ickjai Lee

Recently, a few Seq2Seq based approaches have been proposed, but one of the drawbacks of Seq2Seq models is that, small errors can accumulate quickly along the generated sequence at the inference stage due to the different distributions of training and inference phase.

Spatio-Temporal Forecasting

Sentiment Clustering with Topic and Temporal Information from Large Email Dataset

no code implementations • PACLIC 2016 • Sisi Liu, Ickjai Lee, Guochen Cai

Clustering Sentiment Analysis +1