Wikipedia-based Kernels for dialogue topic tracking
Seokhwan Kim, Rafael E. Banchs, Haizhou Li · 2014
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.