A Class-specific Copy Network for Handling the Rare Word Problem in Neural Machine Translation

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	A Class-specific Copy Network for Handling the Rare Word Problem in Neural Machine Translation
	Feng Wang; Wei Chen; Zhen yang; Xiaowei Zhang; Shuang Xu; Bo Xu
	2017
会议日期	14-19 May 2017
会议地点	Anchorage, AK, USA
关键词	Neural Machine Translation (Nmt) Copy Network Rare Word
页码	2658-2664
英文摘要	Neural machine translation (NMT) has shown promising results and rapidly gained adoption in many large-scale settings. With the NMT model being widely used in empirical productions, its long-standing weakness in handling the rare and out of vocabulary words has been amplified a lot. In order to release the model from the stress of “understanding” the rare words, copy mechanism has been proposed to deal with the rare and unseen words for the neural network models using attention. However the negative side of the copy mechanism is that the model is only able to decide whether to copy or not. It is unable to detect which class should the rare word be copied to, such as person, location, and organization. This paper deeply investigates this limitation of the NMT model. As a result, we propose a new NMT model by novelly incorporating a class-specific copy network. With the network, the proposed NMT model is able to decide which class the words in the target belong to and which class in the source should be copied to. Experimental results on Chinese-English translation tasks show that the proposed model outperforms the traditional NMT model with a large margin especially for sentences containing the rare words.
会议录	IJCNN
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/41055]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Wei Chen
推荐引用方式 GB/T 7714	Feng Wang,Wei Chen,Zhen yang,et al. A Class-specific Copy Network for Handling the Rare Word Problem in Neural Machine Translation[C]. 见:. Anchorage, AK, USA. 14-19 May 2017.