Sequence Generation: From Both Sides to the Middle | |
Zhou, Long1,3; Zhang, Jiajun1,3; Zong, Chengqing1,3,4; Yu, Heng2 | |
2019-08 | |
会议日期 | August 10-16, 2019 |
会议地点 | Macao, China |
英文摘要 | The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token from left to right, hence (1) this autoregressive decoding procedure is time-consuming when the output sentence becomes longer, and (2) it lacks the guidance of future context which is crucial to avoid under-translation. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/39588] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.National Laboratory of Pattern Recognition, CASIA, Beijing, China 2.Machine Intelligence Technology Lab, Alibaba Group 3.University of Chinese Academy of Sciences, Beijing, China 4.CAS Center for Excellence in Brain Science and Intelligence Technology, Shanghai, China |
推荐引用方式 GB/T 7714 | Zhou, Long,Zhang, Jiajun,Zong, Chengqing,et al. Sequence Generation: From Both Sides to the Middle[C]. 见:. Macao, China. August 10-16, 2019. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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