Self-Modifying State Modeling for Simultaneous Machine Translation
Donglei, Yu2,3; Xiaomian, Kang2,3; Yuchen, Liu2,3; YU, Zhou1,2; Chengqing, Zong2,3
2024
会议日期August 11–16, 2024
会议地点Bangkok, Thailand
英文摘要

Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, whose decisions form a decision path. Existing SiMT methods, which learn the policy by exploring various decision paths in training, face inherent limitations. These methods not only fail to precisely optimize the policy due to the inability to accurately assess the individual impact of each decision on SiMT performance, but also cannot sufficiently explore all potential paths because of their vast number. Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models. To solve these issues, we propose Self-Modifying State Modeling (SM2), a novel training paradigm for SiMT task. Without building decision paths, SM2 individually optimizes decisions at each state during training. To precisely optimize the policy, SM2 introduces Self-Modifying process to independently assess and adjust decisions at each state. For sufficient exploration, SM2 proposes Prefix Sampling to efficiently traverse all potential states. Moreover, SM2 ensures compatibility with bidirectional encoders, thus achieving higher translation quality. Experiments show that SM2 outperforms strong baselines. Furthermore, SM2 allows offline machine translation models to acquire SiMT ability with fine-tuning.

语种英语
内容类型会议论文
源URL[http://ir.ia.ac.cn/handle/173211/57442]  
专题模式识别国家重点实验室_自然语言处理
通讯作者YU, Zhou
作者单位1.Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd
2.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences
3.School of Artificial Intelligence, University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Donglei, Yu,Xiaomian, Kang,Yuchen, Liu,et al. Self-Modifying State Modeling for Simultaneous Machine Translation[C]. 见:. Bangkok, Thailand. August 11–16, 2024.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。


©版权所有 ©2017 CSpace - Powered by CSpace