Knowledge Commons of Institute of Automation,CAS
Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task | |
Ma, Cong1,2![]() ![]() ![]() ![]() ![]() | |
2022-08 | |
会议名称 | 2022 26th International Conference on Pattern Recognition (ICPR) |
会议录名称 | Proceedings of the 26th International Conference on Pattern Recognition (ICPR 2022) |
会议日期 | August 21-25, 2022 |
会议地点 | Montréal, Québec, Canada |
摘要 | 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. |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/57609 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Zhang, Yaping |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, P.R. China 2.National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, No.95 Zhongguan East Road, Beijing 100190, P.R. China 3.Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd, Beijing 100190, P.R. China 4.Samsung Research China - Beijing (SRC-B) |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Ma, Cong,Zhang, Yaping,Tu, Mei,et al. Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-ICPR2022-IEEE_Vers(1891KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论