Transferable dialogue systems and user simulators

BH Tseng, Y Dai, F Kreyssig, B Byrne - ar** personalized Task-oriented Dialogue Systems
(TDSs). Previous work on personalized TDSs often assumes that complete user profiles are …

ReMeDi: Resources for multi-domain, multi-service, medical dialogues

G Yan, J Pei, P Ren, Z Ren, X **n, H Liang… - Proceedings of the 45th …, 2022 - dl.acm.org
\AcpMDS aim to assist doctors and patients with a range of professional medical services, ie,
diagnosis, treatment and consultation. The development of\acpMDS is hindered because of …

Learning expressive meta-representations with mixture of expert neural processes

Q Wang, H Van Hoof - Advances in neural information …, 2022 - proceedings.neurips.cc
Neural processes (NPs) formulate exchangeable stochastic processes and are promising
models for meta learning that do not require gradient updates during the testing phase …

Mixture-of-Languages Routing for Multilingual Dialogues

J Pei, G Yan, M De Rijke, P Ren - ACM Transactions on Information …, 2024 - dl.acm.org
We consider multilingual dialogue systems and ask how the performance of a dialogue
system can be improved by using information that is available in other languages than the …

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue

H Du, S Li, M Wu, X Feng, YF Li, H Wang - arxiv preprint arxiv:2406.14457, 2024 - arxiv.org
Reinforcement learning (RL) is a powerful approach to enhance task-oriented dialogue
(TOD) systems. However, existing RL methods tend to mainly focus on generation tasks …

Diversifying task-oriented dialogue response generation with prototype guided paraphrasing

P Lippe, P Ren, H Haned, B Voorn… - arxiv preprint arxiv …, 2020 - arxiv.org
Existing methods for Dialogue Response Generation (DRG) in Task-oriented Dialogue
Systems (TDSs) can be grouped into two categories: template-based and corpus-based …

[PDF][PDF] Wizard of Search Engine

P Ren, Z Liu, X Song, H Tian, Z Chen, Z Ren… - Proceedings of the …, 2021 - academia.edu
Conversational information seeking (CIS) is playing an increasingly important role in
connecting people to information. Due to a lack of suitable resources, previous studies on …