This paper investigates whether a customer care dialog system can be built automatically by mining and leveraging the wealth of information on a company's website. Our objective is to allow the users to ask FAQ-like questions which may request a specific piece of information, an analytical answer, or a transaction such as checking the status of the payment. We developed an infrastructure, referred to as WebTalk, that constructs different application-specific dialog systems by taking different websites as input. In this paper, we overview the involved technologies in WebTalk, address the challenges that will be shown very different from those in traditional dialog systems, and describe our efforts to approach these challenges. We present an evaluation for one WebTalk component: website based question answering.
Cite as: Feng, J., Reddy, S., Saraçlar, M. (2005) Webtalk: mining websites for interactively answering questions. Proc. Interspeech 2005, 2485-2488, doi: 10.21437/Interspeech.2005-409
@inproceedings{feng05_interspeech,
author={Junlan Feng and Srihari Reddy and Murat Saraçlar},
title={{Webtalk: mining websites for interactively answering questions}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={2485--2488},
doi={10.21437/Interspeech.2005-409}
}