Knowledge Commons of Institute of Automation,CAS
Self-Modifying State Modeling for Simultaneous Machine Translation | |
Donglei, Yu1,2; Xiaomian, Kang1,2![]() ![]() ![]() | |
2024 | |
会议名称 | The 62nd Annual Meeting of the Association for Computational Linguistics |
会议日期 | August 11–16, 2024 |
会议地点 | Bangkok, Thailand |
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. |
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 | 语音语言处理 |
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/173211/57442 |
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 | YU, Zhou |
作者单位 | 1.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Fanyu AI Laboratory, Zhongke Fanyu Technology Co., Ltd |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
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],2024. |
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 | ||
1699_self_modifying_(924KB) | 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