Paper Info
Title
Hybrid approach to user intention modeling for dialog simulation
Abstract
This paper proposes a novel user intention simulation method which is a data-driven approach but able to integrate diverse user discourse knowledge together to simulate various type of users. In Markov logic framework, logistic regression based data-driven user intention modeling is introduced, and human dialog knowledge are designed into two layers such as domain and discourse knowledge, then it is integrated with the data-driven model in generation time. Cooperative, corrective and self-directing discourse knowledge are designed and integrated to mimic such type of users. Experiments were carried out to investigate the patterns of simulated users, and it turned out that our approach was successful to generate user intention patterns which are not only unseen in the training corpus and but also personalized in the designed direction.
Year
Venue
Keywords
2009
ACL/IJCNLP (Short Papers)
diverse user discourse knowledge,discourse knowledge,novel user intention simulation,user intention pattern,hybrid approach,dialog simulation,data-driven model,data-driven user intention modeling,human dialog knowledge,data-driven approach,simulated user,self-directing discourse knowledge,logical framework,user experience
Field
DocType
Volume
Dialog box,Computer science,Markov chain,Human–computer interaction,Artificial intelligence,User modeling,Natural language processing,Machine learning
Conference
P09-2
Citations 
PageRank 
References 
8
0.84
7
Authors
4
Name
Order
Citations
PageRank
Sangkeun Jung119715.23
Cheongjae Lee220615.99
Kyungduk Kim315412.10
Gary Geunbae Lee493293.23