no code implementations • 25 Feb 2022 • Kaining Mao, Wei zhang, Deborah Baofeng Wang, Ang Li, Rongqi Jiao, Yanhui Zhu, Bin Wu, Tiansheng Zheng, Lei Qian, Wei Lyu, Minjie Ye, Jie Chen
For the text modality, we use global vectors for word representation (GloVe) to perform word embeddings and the embeddings are fed into the Bi-LSTM network.