" Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking

L Jacqmin, LM Rojas-Barahona, B Favre - arXiv preprint arXiv:2207.14627, 2022 - arxiv.org
While communicating with a user, a task-oriented dialogue system has to track the user's
needs at each turn according to the conversation history. This process called dialogue state …

AI robustness: a human-centered perspective on technological challenges and opportunities

A Tocchetti, L Corti, A Balayn, M Yurrita… - ACM Computing …, 2022 - dl.acm.org
Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness
remains elusive and constitutes a key issue that impedes large-scale adoption. Besides …

Show, don't tell: demonstrations outperform descriptions for schema-guided task-oriented dialogue

R Gupta, H Lee, J Zhao, A Rastogi, Y Cao… - arXiv preprint arXiv …, 2022 - arxiv.org
Building universal dialogue systems that operate across multiple domains/APIs and
generalize to new ones with minimal overhead is a critical challenge. Recent works have …

Personalizing task-oriented dialog systems via zero-shot generalizable reward function

AB Siddique, MH Maqbool, K Taywade… - Proceedings of the 31st …, 2022 - dl.acm.org
Task-oriented dialog systems enable users to accomplish tasks using natural language.
State-of-the-art systems respond to users in the same way regardless of their personalities …

GenTUS: Simulating user behaviour and language in task-oriented dialogues with generative transformers

H Lin, C Geishauser, S Feng, N Lubis… - arXiv preprint arXiv …, 2022 - arxiv.org
User simulators (USs) are commonly used to train task-oriented dialogue systems (DSs) via
reinforcement learning. The interactions often take place on semantic level for efficiency, but …

Enhancing performance on seen and unseen dialogue scenarios using retrieval-augmented end-to-end task-oriented system

J Zhang, S Roller, K Qian, Z Liu, R Meng… - arXiv preprint arXiv …, 2023 - arxiv.org
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by
leveraging sophisticated natural language understanding and natural language generation …

Information extraction and human-robot dialogue towards real-life tasks: A baseline study with the mobilecs dataset

H Liu, H Peng, Z Ou, J Li, Y Huang, J Feng - arXiv preprint arXiv …, 2022 - arxiv.org
Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected
through Wizard-of-Oz simulated games. However, the Wizard-of-Oz data are in fact …

Injecting Comparison Skills in Task-Oriented Dialogue Systems for Database Search Results Disambiguation

Y Kim, Y Hwang, J Shin, H Bae… - Findings of the …, 2023 - aclanthology.org
In task-oriented dialogue (TOD) systems designed to aid users accomplish specific goals in
one or more domains, the agent retrieves entities that satisfy user constraints from the …

Are LLMs Robust for Spoken Dialogues?

SM Mousavi, G Roccabruna, S Alghisi… - arXiv preprint arXiv …, 2024 - arxiv.org
Large Pre-Trained Language Models have demonstrated state-of-the-art performance in
different downstream tasks, including dialogue state tracking and end-to-end response …

The StatCan dialogue dataset: Retrieving data tables through conversations with genuine intents

XH Lu, S Reddy, H de Vries - arXiv preprint arXiv:2304.01412, 2023 - arxiv.org
We introduce the StatCan Dialogue Dataset consisting of 19,379 conversation turns
between agents working at Statistics Canada and online users looking for published data …