Stochastic web-based natural language dialog planning for web information filtering

This work addresses natural language dialog planning for an intelligent web filtering model, which lets the user filter search results obtained by a traditional search engine and assists them to find what they really are looking for. Unlike state-of-the-art approaches, a stochastic planning model is proposed for a web-driven dialog system which uses Conditional Random Fields to predict next dialog moves. Experiments with real web users and different interaction settings show the promise of the approach to web-based adaptive planning aimed at information filtering.