no code implementations • EMNLP (IWSLT) 2019 • Mei Tu, Wei Liu, Lijie Wang, Xiao Chen, Xue Wen
We propose layer-tied self-attention for end-to-end speech translation.
no code implementations • ACL 2022 • Yimeng Zhuang, Jing Zhang, Mei Tu
(2) A sparse attention matrix estimation module, which predicts dominant elements of an attention matrix based on the output of the previous hidden state cross module.
no code implementations • 9 May 2023 • Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong
Text image machine translation (TIMT) has been widely used in various real-world applications, which translates source language texts in images into another target language sentence.
1 code implementation • 9 May 2023 • Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong
Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models.
no code implementations • 6 May 2023 • Fan Zhang, Mei Tu, Sangha Kim, Song Liu, Jinyao Yan
Our model is composed of three parts: a backbone model, a domain discriminator taking responsibility to discriminate data from different domains, and a set of experts that transfer the decoded features from generic to specific.
1 code implementation • 8 Oct 2022 • Cong Ma, Yaping Zhang, Mei Tu, Xu Han, Linghui Wu, Yang Zhao, Yu Zhou
End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research.
1 code implementation • 18 Jul 2022 • Bohua Peng, Mobarakol Islam, Mei Tu
In this work, we propose Angular Gap, a measure of difficulty based on the difference in angular distance between feature embeddings and class-weight embeddings built by hyperspherical learning.