Knowledge Commons of Institute of Automation,CAS
Adapting translation models for transcript disfluency detection | |
Dong QQ(董倩倩)1,2; Feng Wang(王峰)1; Zhen Yang(杨振)1,2; Wei Chen(陈炜)1; Shuang Xu(徐爽)1; Bo Xu(徐波)1,2 | |
2019-02 | |
会议名称 | In Proceedings of the33th AAAI Conference on Artificial Intelligence (AAAI-2019) |
会议日期 | 2019-2 |
会议地点 | Hawaii |
摘要 | Transcript disfluency detection (TDD) is an important com- ponent of the real-time speech translation system, which arouses more and more interests in recent years. This pa- per presents our study on adapting neural machine transla- tion (NMT) models for TDD. We propose a general training framework for adapting NMT models to TDD task rapidly. In this framework, the main structure of the model is imple- mented similar to the NMT model. Additionally, several ex- tended modules and training techniques which are indepen- dent of the NMT model are proposed to improve the perfor- mance, such as the constrained decoding, denoising autoen- coder initialization and a TDD-specific training object. With the proposed training framework, we achieve significant im- provement. However, it is too slow in decoding to be prac- tical. To build a feasible and production-ready solution for TDD, we propose a fast non-autoregressive TDD model fol- lowing the non-autoregressive NMT model emerged recently. Even we do not assume the specific architecture of the NMT model, we build our TDD model on the basis of Transformer, which is the state-of-the-art NMT model. We conduct exten- sive experiments on the publicly available set, Switchboard, and in-house Chinese set. Experimental results show that the proposed model significantly outperforms previous state-of- the-art models. |
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 | 其他 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/44965 |
专题 | 复杂系统认知与决策实验室_听觉模型与认知计算 |
通讯作者 | Bo Xu(徐波) |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China 2.University of Chinese Academy of Sciences, Beijing, China |
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 | Dong QQ,Feng Wang,Zhen Yang,et al. Adapting translation models for transcript disfluency detection[C],2019. |
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 | ||
Adapting Translation(287KB) | 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