A Flexible Schema-Guided Dialogue Management Framework: From Friendly Peer to Virtual Standardized Cancer Patient

  title={A Flexible Schema-Guided Dialogue Management Framework: From Friendly Peer to Virtual Standardized Cancer Patient},
  author={Benjamin Kane and Catherine Giugno and Len Schubert and Kurtis Glenn Haut and Caleb Wohn and Ehsan Hoque},
A schema-guided approach to dialogue management has been shown in recent work to be effective in creating robust customizable virtual agents capable of acting as friendly peers or task assistants. However, successful applications of these methods in open-ended, mixed-initiative domains remain elu-sive – particularly within medical domains such as virtual standardized patients, where such complex interactions are commonplace – and require more extensive and flexible dialogue management… 

Figures and Tables from this paper

Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset

This work introduces the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains, and presents a schema-guided paradigm for task-oriented dialogue, in which predictions are made over a dynamic set of intents and slots provided as input.

Managing Casual Spoken Dialogue Using Flexible Schemas , Pattern Transduction Trees , and Gist Clauses

This work uses script-like schemas to loosely guide the dialogue, where the steps of a schema are specified in a declarative language that allows for both explicit and abstract description of speech acts.

Human-Centered Distributed Conversational Modeling: Efficient Modeling of Robust Virtual Human Conversations

This work presents a new approach called Human-centered Distributed Conversational Modeling, using this approach, users create conversational models in a distributed manner, which results in more comprehensive coverage of the conversational space.

Novel Computational Linguistic Measures, Dialogue System and the Development of SOPHIE: Standardized Online Patient for Healthcare Interaction Education

Methods for the automatic detection of two behavioral paradigms, lecturing and positive language usage patterns (sentiment trajectory of conversation), that are shown to be significantly associated with patient prognosis understanding are developed.

Mixed Initiative in Dialogue: An Investigation into Discourse Segmentation

A set of rules for the transfer of control is applied to 4 sets of dialogues and it is found that both allocation of control and the manner in which control is transferred is radically different for the two dialogue types.

DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation

It is shown that conversational systems that leverage DialoGPT generate more relevant, contentful and context-consistent responses than strong baseline systems.

Dialogue Design and Management for Multi-Session Casual Conversation with Older Adults

An automatic spoken dialogue manager is described for LISSA, an on-screen virtual agent that can keep older users involved in conversations over several sessions, each lasting 10-20 minutes.

Developing a Conversational Virtual Standardized Patient to Enable Students to Practice History-Taking Skills

The virtual standardized patients described herein represent standardized patients that students interview using natural language that students take histories and develop differential diagnoses of the VSPs as much as they would with standardized or actual patients.

Towards Natural Language Story Understanding with Rich Logical Schemas

This work provides a learning system with a “head start” consisting of a semantic parser, some basic ontological knowledge, and most importantly, a small set of very general schemas about the kinds of patterns of events that even a one- or two-year-old could reasonably be presumed to possess.

Schema-Guided Paradigm for Zero-Shot Dialog

The Schema Attention Model (SAM) is introduced and improved schema representations for the STAR corpus are introduced and validated the feasibility of zero-shot generalizability in dialog.