Papers by Shaojie Bai
Multimodal Transformer for Unaligned Multimodal Language Sequences (P19-1)
Copied to clipboard
Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, Ruslan Salakhutdinov
| Challenge: | Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors. |
| Approach: | They propose a multimodal model that extends the standard Transformer network to learn representations directly from unaligned multimodal streams. |
| Outcome: | The proposed model outperforms state-of-the-art methods on aligned and non-aligned data. |
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel (D19-1)
Copied to clipboard
| Challenge: | Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. |
| Approach: | They propose a new formulation of attention via the lens of the kernel which allows us to understand individual components of Transformer's attention. |
| Outcome: | The proposed model outperforms existing models on language understanding and sequence prediction tasks and is more efficient than existing models. |