Chinese spoken language understanding with conditional random fields
Weidong Zhou, Baozong Yuan, Zhenjiang Miao, Weibin Zhu, Weibin Liu · 2008
This paper presents a new approach to spoken language understanding tagging for Chinese texts using conditional random fields (CRFs). SLU for spoken dialog system, especially the slot-filling problem is solved as a sequential labeling problem. The experimental results show that this approach has good performance and is feasible for the restricted domain oriented Chinese spoken language understanding.