Knowledge Commons of Institute of Automation,CAS
Contrastive Adversarial Training for Multi-Modal Machine Translation | |
Huang X(黄鑫)1,2; Zhang JJ(张家俊)1,2; Zong CQ(宗成庆)1,2 | |
发表期刊 | ACM Transactions on Asian and Low-Resource Language Information Processing |
2023-06 | |
卷号 | 22期号:6页码:157:1-18 |
摘要 | The multi-modal machine translation task is to improve translation quality with the help of additional visual input. It is expected to disambiguate or complement semantics while there are ambiguous words or incomplete expressions in the sentences. Existing methods have tried many ways to fuse visual information into text representations. However, only a minority of sentences need extra visual information as complementary. Without guidance, models tend to learn text-only translation from the major well-aligned translation pairs. In this article, we propose a contrastive adversarial training approach to enhance visual participation in semantic representation learning. By contrasting multi-modal input with the adversarial samples, the model learns to identify the most informed sample that is coupled with a congruent image and several visual objects extracted from it. This approach can prevent the visual information from being ignored and further fuse cross-modal information. We examine our method in three multi-modal language pairs. Experimental results show that our model is capable of improving translation accuracy. Further analysis shows that our model is more sensitive to visual information. |
关键词 | contrastive learning adversarial training multi-modal machine translation |
收录类别 | SCI |
语种 | 英语 |
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 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52142 |
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 | Zong CQ(宗成庆) |
作者单位 | 1.中国科学院自动化研究所模式识别国家重点实验室 2.中国科学院大学人工智能学院 |
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 | Huang X,Zhang JJ,Zong CQ. Contrastive Adversarial Training for Multi-Modal Machine Translation[J]. ACM Transactions on Asian and Low-Resource Language Information Processing,2023,22(6):157:1-18. |
APA | Huang X,Zhang JJ,&Zong CQ.(2023).Contrastive Adversarial Training for Multi-Modal Machine Translation.ACM Transactions on Asian and Low-Resource Language Information Processing,22(6),157:1-18. |
MLA | Huang X,et al."Contrastive Adversarial Training for Multi-Modal Machine Translation".ACM Transactions on Asian and Low-Resource Language Information Processing 22.6(2023):157:1-18. |
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 | ||
tallip.published.202(2387KB) | 期刊论文 | 出版稿 | 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