Title :
Wikipedia-based Kernels for dialogue topic tracking
Author :
Seokhwan Kim ; Banchs, Rafael E. ; Haizhou Li
Author_Institution :
Human Language Technol. Dept., Inst. for Infocomm Res., Singapore, Singapore
Abstract :
Dialogue topic tracking aims to segment on-going dialogues into topically coherent sub-dialogues and predict the topic category for each next segment. This paper proposes a kernel method for dialogue topic tracking to utilize various types of information obtained from Wikipedia. The experimental results show that our proposed approach can significantly improve the performances of the task in mixed-initiative human-human dialogues.
Keywords :
Web sites; interactive systems; pattern classification; Wikipedia-based kernels; dialogue topic tracking; kernel method; mixed-initiative human-human dialogues; topic category prediction; Electronic publishing; Encyclopedias; Internet; Kernel; Semantics; Vectors; Dialogue Topic Tracking; Kernel Methods; Spoken Dialogue Systems; Wikipedia;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
Conference_Location :
Florence
DOI :
10.1109/ICASSP.2014.6853572
