In-context learning for few-shot dialogue state tracking

Y Hu, CH Lee, T Xie, T Yu, NA Smith… - arXiv preprint arXiv …, 2022 - arxiv.org
Collecting and annotating task-oriented dialogues is time-consuming and costly; thus, zero
and few shot learning could greatly benefit dialogue state tracking (DST). In this work, we …

" 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 …

Leveraging slot descriptions for zero-shot cross-domain dialogue state tracking

Z Lin, B Liu, S Moon, P Crook, Z Zhou, Z Wang… - arXiv preprint arXiv …, 2021 - arxiv.org
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented
dialogue in unseen domains without the expense of collecting in-domain data. In this paper …

Multiwoz 2.4: A multi-domain task-oriented dialogue dataset with essential annotation corrections to improve state tracking evaluation

F Ye, J Manotumruksa, E Yilmaz - arXiv preprint arXiv:2104.00773, 2021 - arxiv.org
The MultiWOZ 2.0 dataset has greatly stimulated the research of task-oriented dialogue
systems. However, its state annotations contain substantial noise, which hinders a proper …

Dialogue state tracking with a language model using schema-driven prompting

CH Lee, H Cheng, M Ostendorf - arXiv preprint arXiv:2109.07506, 2021 - arxiv.org
Task-oriented conversational systems often use dialogue state tracking to represent the
user's intentions, which involves filling in values of pre-defined slots. Many approaches have …

Dynamic schema graph fusion network for multi-domain dialogue state tracking

Y Feng, A Lipani, F Ye, Q Zhang, E Yilmaz - arXiv preprint arXiv …, 2022 - arxiv.org
Dialogue State Tracking (DST) aims to keep track of users' intentions during the course of a
conversation. In DST, modelling the relations among domains and slots is still an under …

Cyber sentinel: Exploring conversational agents in streamlining security tasks with gpt-4

M Kaheh, DK Kholgh, P Kostakos - arXiv preprint arXiv:2309.16422, 2023 - arxiv.org
In an era where cyberspace is both a battleground and a backbone of modern society, the
urgency of safeguarding digital assets against ever-evolving threats is paramount. This …

BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking

S Won, H Kwak, J Shin, J Han… - Proceedings of the 61st …, 2023 - aclanthology.org
Despite the recent advances in dialogue state tracking (DST), the joint goal accuracy (JGA)
of the existing methods on MultiWOZ 2.1 still remains merely 60%. In our preliminary error …

Divide, conquer, and combine: Mixture of semantic-independent experts for zero-shot dialogue state tracking

Q Wang, L Ding, Y Cao, Y Zhan, Z Lin, S Wang… - arXiv preprint arXiv …, 2023 - arxiv.org
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of
task-oriented dialogue domains without the cost of collecting in-domain data. Existing works …

ASSIST: Towards label noise-robust dialogue state tracking

F Ye, Y Feng, E Yilmaz - arXiv preprint arXiv:2202.13024, 2022 - arxiv.org
The MultiWOZ 2.0 dataset has greatly boosted the research on dialogue state tracking
(DST). However, substantial noise has been discovered in its state annotations. Such noise …