papers

Publications (5)

cs.CL2023

Label-Free Multi-Domain Machine Translation with Stage-wise Training

Fan Zhang, Mei Tu, Sangha Kim +2

Most multi-domain machine translation models rely on domain-annotated data. Unfortunately, domain labels are usually unavailable in both training processes and real translation sce…

cs.CL2023

E2TIMT: Efficient and Effective Modal Adapter for Text Image Machine Translation

Cong Ma, Yaping Zhang, Mei Tu +3

Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and o…

cs.CV2022

Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration

Bohua Peng, Mobarakol Islam, Mei Tu

Curriculum learning needs example difficulty to proceed from easy to hard. However, the credibility of image difficulty is rarely investigated, which can seriously affect the effec…

cs.CL2022

Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task

Cong Ma, Yaping Zhang, Mei Tu +4

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 resear…

cs.CL2023

Multi-Teacher Knowledge Distillation For Text Image Machine Translation

Cong Ma, Yaping Zhang, Mei Tu +3

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 sentenc…