M
Milica Gasic
Researcher at University of Düsseldorf
Publications - 138
Citations - 10182
Milica Gasic is an academic researcher from University of Düsseldorf. The author has contributed to research in topics: Reinforcement learning & Partially observable Markov decision process. The author has an hindex of 41, co-authored 129 publications receiving 8554 citations. Previous affiliations of Milica Gasic include Saarland University & University of Cambridge.
Papers
More filters
Journal ArticleDOI
POMDP-Based Statistical Spoken Dialog Systems: A Review
TL;DR: This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.
Proceedings ArticleDOI
A Network-based End-to-End Trainable Task-oriented Dialogue System
Tsung-Hsien Wen,David Vandyke,Nikola Mrkšić,Milica Gasic,Lina Maria Rojas-Barahona,Pei-Hao Su,Stefan Ultes,Steve Young +7 more
TL;DR: The authors introduced a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework.
Proceedings ArticleDOI
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
TL;DR: A statistical language generator based on a semantically controlled Long Short-term Memory (LSTM) structure that can learn from unaligned data by jointly optimising sentence planning and surface realisation using a simple cross entropy training criterion, and language variation can be easily achieved by sampling from output candidates.
Posted Content
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling
Paweł Budzianowski,Tsung-Hsien Wen,Bo-Hsiang Tseng,Iñigo Casanueva,Stefan Ultes,Osman Ramadan,Milica Gasic +6 more
TL;DR: The Multi-Domain Wizard-of-Oz dataset (MultiWOZ) as discussed by the authors is a fully-labeled collection of human-human written conversations spanning over multiple domains and topics.
Journal ArticleDOI
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management
Steve Young,Milica Gasic,Simon Keizer,François Mairesse,Jost Schatzmann,Blaise Thomson,Kai Yu +6 more
TL;DR: This paper explains how Partially Observable Markov Decision Processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialogue systems and describes a form of approximation called the Hidden Information State model which does scale and which can be used to build practical systems.