The RavenClaw dialog management framework: Architecture and systems

By Dan Bohus, Alexander I. Rudnicky. Computer Speech and Language, 2009

311 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Attention with Intention for a Neural Network Conversation Model (2015, background): “Conversation models have been typically designed to be domain specific with much knowledge such as rules [3,18].”
Dialogue Transformers (2019, background): “In the 1980s, Groz and Sidner [3] argued for representing dialogue history as a stack of topics, and later the RavenClaw [4] dialogue system implemented a dialogue stack for the speciﬁc purpose of handling sub-dialogues.”
Neural Approaches to Conversational AI (2018, unknown): “systems. A comprehensive survey is out of the scope of the this chapter. Interested readers are referred to earlier examples (Cole, 1999; Larsson and Traum, 2000; Rich et al., 2001; Bos et al., 2003; Bohus and Rudnicky, 2009), as well as excellent surveys like McTear (2002) and Young et al. (2013) f”
Rasa: Open Source Language Understanding and Dialogue Management (2017, methodology): “Other open toolkits include OpenDial [7] and RavenClaw [1].”
Using General-Purpose Planning for Action Selection in Human-Robot Interaction (2016, background): “An important direction in interactive systems research has been the development of toolkits that support their construction (Rich and Sidner 1998; Larsson and Traum 2000; Bohus and Rudnicky 2009; Lison 2015).”