1 code implementation • 30 Nov 2022 • Qi Zhu, Christian Geishauser, Hsien-Chin Lin, Carel van Niekerk, Baolin Peng, Zheng Zhang, Michael Heck, Nurul Lubis, Dazhen Wan, Xiaochen Zhu, Jianfeng Gao, Milica Gašić, Minlie Huang
To address this issue, we present ConvLab-3, a flexible dialogue system toolkit based on a unified TOD data format.
They are ideally evaluated with human users, which however is unattainable to do at every iteration of the development phase.
In addition, its behaviour can be further shaped with reinforcement learning opening the door to training specialised user simulators.
The lack of a framework with training protocols, baseline models and suitable metrics, has so far hindered research in this direction.
Our architecture and training strategies improve robustness towards sample sparsity, new concepts and topics, leading to state-of-the-art performance on a range of benchmarks.
The dialogue management component of a task-oriented dialogue system is typically optimised via reinforcement learning (RL).
We report a set of experimental results to show the usability of this corpus for emotion recognition and state tracking in task-oriented dialogues.
Ranked #1 on Emotion Recognition in Conversation on EmoWoz
This highlights the importance of developing neural dialogue belief trackers that take uncertainty into account.
TUS can compete with rule-based user simulators on pre-defined domains and is able to generalise to unseen domains in a zero-shot fashion.
Dialog state tracking (DST) suffers from severe data sparsity.
In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning.
The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system.
In this paper we present a new approach to DST which makes use of various copy mechanisms to fill slots with values.
Ranked #10 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1