The MaDrIgAL project: Multi-Dimensional Interaction Management and Adaptive Learning

Simon Keizer, Verena Rieser

Research output: Contribution to conferencePaper

88 Downloads (Pure)

Abstract

Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems. However, they still lack in two main aspects: 1) their perceived naturalness and social intelligence, and 2) their cross-domain scalability. In this paper, we argue that both of these shortcomings can be addressed effectively by extending current models to reflect and exploit the multi-dimensional nature of human dialogue. In order to investigate this, the MaDrIgAL project aims to develop multi-dimensional versions of data-driven models for spoken dialogue systems. In doing so, we 1) incorporate a richer set of dialogue acts into the learning process, leading to more natural and socially appropriate dialogues, and 2) learn transferable skills by separating out domain-independent dimensions of communication, leading to more efficient cross-domain adaptation.
Original languageEnglish
Number of pages6
Publication statusPublished - 23 Sep 2016
Event1st International Workshop on Domain Adaptation for Dialog Agents 2016 - Riva del Garda Fierecongressi, Riva del Garda, Italy
Duration: 23 Sep 201623 Sep 2016
https://sites.google.com/site/ecmldaworkshop/home

Workshop

Workshop1st International Workshop on Domain Adaptation for Dialog Agents 2016
Abbreviated titleDADA
CountryItaly
CityRiva del Garda
Period23/09/1623/09/16
Internet address

Keywords

  • Spoken Dialogue Systems
  • machine learning
  • domain adaptation

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'The MaDrIgAL project: Multi-Dimensional Interaction Management and Adaptive Learning'. Together they form a unique fingerprint.

Cite this