A composite kernel approach for dialog topic tracking with structured domain knowledge from Wikipedia
|A composite kernel approach for dialog topic tracking with structured domain knowledge from Wikipedia|
|Author(s)||Kim S., Banchs R.E., Li H.|
|Published in||52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference|
|Keyword(s)||Unknown (Extra: Computational linguistics, Composite kernels, Domain knowledge, Mixed-initiative, Structured domain knowledge, Topic tracking, Topic transition, Wikipedia, Information analysis)|
|Article||BASE, CiteSeerX, Google Scholar|
|Web||Ask, Bing, Google (PDF), Yahoo!|
|Download and mirrors|
|Local copy||Not available|
|Remote mirror(s)||Not available|
|Export and share|
|BibTeX, CSV, RDF, JSON|
|Browse properties · List of conference papers|
A composite kernel approach for dialog topic tracking with structured domain knowledge from Wikipedia is a 2014 conference paper written in English by Kim S., Banchs R.E., Li H. and published in 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings of the Conference.
Dialog topic tracking aims at analyzing and maintaining topic transitions in ongoing dialogs. This paper proposes a composite kernel approach for dialog topic tracking to utilize various types of domain knowledge obtained from Wikipedia. Two kernels are defined based on history sequences and context trees constructed based on the extracted features. The experimental results show that our composite kernel approach can significantly improve the performances of topic tracking in mixed-initiative human-human dialogs.
- This section requires expansion. Please, help!
Probably, this publication is cited by others, but there are no articles available for them in WikiPapers.