Self-Attention Based Network for Punctuation Restoration

	Self-Attention Based Network for Punctuation Restoration
	Feng Wang; Wei Chen; Zhen Yang; Bo Xu
	2018
会议名称	International Conference on Pattern Recognition
会议日期	August 20th-24th 2018
会议地点	In Beijing, China
摘要	Inserting proper punctuation into Automatic Speech Recognizer(ASR) transcription is a challenging and promising task in real-time Spoken Language Translation(SLT). Traditional methods built on the sequence labelling framework are weak in handling the joint punctuation. To tackle this problem, we propose a novel self-attention based network, which can solve the aforementioned problem very well. In this work, a light-weight neural net is proposed to extract the hidden features based solely on self-attention without any Recurrent Neural Nets(RNN) and Convolutional Neural Nets(CNN). We conduct extensive experiments on complex punctuation tasks. The experimental results show that the proposed model achieves significant improvements on joint punctuation task while being superior to traditional methods on simple punctuation task as well.
关键词	Punctuation Restoration Self-attention
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/40993
专题	复杂系统认知与决策实验室_听觉模型与认知计算数字内容技术与服务研究中心
通讯作者	Wei Chen
推荐引用方式 GB/T 7714	Feng Wang,Wei Chen,Zhen Yang,et al. Self-Attention Based Network for Punctuation Restoration[C],2018.