no code implementations • 17 Mar 2024 • Zichen Wu, Hsiu-Yuan Huang, Fanyi Qu, Yunfang Wu
To address them, we propose Mixture-of-Prompt-Experts with Block-Aware Prompt Fusion (MoPE-BAF), a novel multi-modal soft prompt framework based on the unified vision-language model (VLM).
no code implementations • COLING 2022 • Zichen Wu, Xin Jia, Fanyi Qu, Yunfang Wu
Specially, we present localness modeling with a Gaussian bias to enable the model to focus on answer-surrounded context, and propose a mask attention mechanism to make the syntactic structure of input passage accessible in question generation process.
Ranked #5 on Question Generation on SQuAD1.1