Feiyu Xu

Feiyu Xu


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 September 2019
Verified
Book Chapter
Closed access
PDF file
FXFeiyu Xu
Feiyu Xu
HUHans Uszkoreit
Hans Uszkoreit
YDYangzhou Du
Yangzhou Du
WFWei Fan
Wei Fan
DZDongyan Zhao
Dongyan Zhao
JZJun Zhu
Jun Zhu

26 September 2018
Verified
Book Chapter
Closed access
PDF file
JTJiang Tian
Jiang Tian
CLCong Li
Cong Li
ZSZhongchao Shi
Zhongchao Shi
FXFeiyu Xu
Feiyu Xu

15 February 2019 in Information
Verified
Journal Article
Open access
PDF file
GZGuoguang Zhao
Guoguang Zhao
JZJianyu Zhao
Jianyu Zhao
YLYang Li
Yang Li
CAChristoph Alt
Christoph Alt
RSRobert Schwarzenberg
Robert Schwarzenberg
FXFeiyu Xu
Feiyu Xu
Human agents in technical customer support provide users with instructional answers to solve a task that would otherwise require a lot of time, money, energy, physical costs. Developing a dialogue system in this domain is challenging due to the broad variety of user questions. Moreover, user questions are noisy (for example, spelling mistakes), redundant and have various natural language expressions. In this work, we introduce a conversational system, MOLI (the name of our dialogue system), to solve customer questions by providing instructional answers from a knowledge base. Our approach combines models for question type and intent category classification with slot filling and a back-end knowledge base for filtering and ranking answers, and uses a dialog framework to actively query the user for missing information. For answer-ranking we find that sequential matching networks and neural multi-perspective sentence similarity networks clearly outperform baseline models, achieving a 43% error reduction. The end-to-end P@1(Precision at top 1) of MOLI was 0.69 and the customers’ satisfaction was 0.73.