Knowledge Commons of Institute of Automation,CAS
Exploiting Knowledge Graph in Neural Machine Translation | |
Yu, Lu1,2; Jiajun, Zhang1,2; Chengqing, Zong1,2,3 | |
2018-10 | |
会议名称 | The 14th China Workshop on Machine Translation (CWMT 2018) |
会议日期 | 2018-10 |
会议地点 | Wuyishan, China |
摘要 | Neural machine translation (NMT) can achieve promising translation quality on resource-rich languages due to end-to-end learning. However, the widely-used NMT system only focuses on modeling the inner mapping from source to target without resorting to external knowledge. In this paper, we take English-Chinese translation as a case study to exploit the use of knowledge graph (KG) in NMT. The main idea is utilizing the entity relations in knowledge graph as constraints to enhance the connections between the source words and their translations. Specifically, we design two kinds of constraints. One is monolingual constraint that employs the entity relations in KG to augment the semantic representation of the source words. The other is bilingual constraint which enforces the entity relations between the source words to be shared by their translations. In this way, external knowledge can participate in the translation process and help to model semantic relationships between source and target words. Experimental results demonstrate that our method outperforms the state-of-the-art system. |
关键词 | 神经机器翻译 |
学科门类 | 工学::计算机科学与技术(可授工学、理学学位) |
收录类别 | EI |
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 | 其他 |
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/173211/52048 |
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 | Jiajun, Zhang |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS 2.University of Chinese Academy of Sciences 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
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 | Yu, Lu,Jiajun, Zhang,Chengqing, Zong. Exploiting Knowledge Graph in Neural Machine Translation[C],2018. |
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 | ||
Exploiting Knowledge(596KB) | 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