Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task
This addresses data limitations in text image translation for researchers and practitioners, though it is incremental as it builds on existing multi-task learning approaches.
The paper tackles data sparsity in end-to-end text image translation by using text translation as an auxiliary task in multi-task learning, showing that their method outperforms existing end-to-end methods and that combining translation and recognition tasks yields better results.
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. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary.