Knowledge Commons of Institute of Automation,CAS
A Comparable Study on Model Averaging, Ensembling and Reranking in NMT | |
Yuchen Liu1,2; Long Zhou1,2; Yining Wang1,2; Yang Zhao1,2; Jiajun Zhang1,2; Chengqing Zong1,2,3 | |
2018-08 | |
会议名称 | The Seventh Conference On Natural Language Processing and Chinese Computing (NLPCC-2018) |
会议日期 | August, 26-30, 2018 |
会议地点 | Hohhot, China |
摘要 | Neural machine translation has become a benchmark method in machine translation. Many novel structures and methods have been proposed to improve the translation quality. However, it is difficult to train and turn parameters. In this paper, we focus on decoding techniques that boost translation performance by utilizing existing models. We address the problem from three aspects — parameter, word and sentence level, corresponding to checkpoint averaging, model ensembling and candidates reranking which all do not need to retrain the model. Experimental results have shown that the proposed decoding approaches can significantly improve the performance over baseline model. |
收录类别 | EI |
资助项目 | National Key Research and Development Program of China[2016QY02D0303] |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44411 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
作者单位 | 1.University of Chinese Academy of Sciences 2.National Laboratory of Pattern Recognition, CASIA 3.CAS Center for Excellence in Brain Science and Intelligence Technology |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yuchen Liu,Long Zhou,Yining Wang,et al. A Comparable Study on Model Averaging, Ensembling and Reranking in NMT[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 | ||
2018-YuchenLiu-nlpcc(431KB) | 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