We present a machine translation framework that can incorporate arbitrary features of both input and output sentences. The core of the approach is a novel decoder based on lattice...
Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the...
This paper describes an implemented model of context-based incremental tactical generation within the Dynamic Syntax framework [1] which directly reflects dialogue phenomena such ...
This paper presents a system that uses the domain name of a German business website to locate its information pages (e.g. company profile, contact page, imprint) and then identifi...
Domain shift is a challenging issue in dialogue management. This paper shows how to extract domain knowledge for dialogue model adaptation. The basic semantic concepts are derived ...