Xiao Sun


2018

pdf
A Syntactically Constrained Bidirectional-Asynchronous Approach for Emotional Conversation Generation
Jingyuan Li | Xiao Sun
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Traditional neural language models tend to generate generic replies with poor logic and no emotion. In this paper, a syntactically constrained bidirectional-asynchronous approach for emotional conversation generation (E-SCBA) is proposed to address this issue. In our model, pre-generated emotion keywords and topic keywords are asynchronously introduced into the process of decoding. It is much different from most existing methods which generate replies from the first word to the last. Through experiments, the results indicate that our approach not only improves the diversity of replies, but gains a boost on both logic and emotion compared with baselines.

2014

pdf
Real Time Early-stage Influenza Detection with Emotion Factors from Sina Microblog
Xiao Sun | Jiaqi Ye | Fuji Ren
Proceedings of the Fifth Workshop on South and Southeast Asian Natural Language Processing

2012

pdf
A MMSM-based Hybrid Method for Chinese MicroBlog Word Segmentation
Xiao Sun | Chengcheng Li | Chenyi Tang | Jiaqi Ye
Proceedings of the Second CIPS-SIGHAN Joint Conference on Chinese Language Processing

2008

pdf
HMM and CRF Based Hybrid Model for Chinese Lexical Analysis
Degen Huang | Xiao Sun | Shidou Jiao | Lishuang Li | Zhuoye Ding | Ru Wan
Proceedings of the Sixth SIGHAN Workshop on Chinese Language Processing