Sgd-x: A benchmark for robust generalization in schema-guided dialogue systems

H Lee, R Gupta, A Rastogi, Y Cao, B Zhang… - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue
research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling …

Schema-guided dialogue state tracking task at DSTC8

A Rastogi, X Zang, S Sunkara, R Gupta… - arxiv preprint arxiv …, 2020 - arxiv.org
This paper gives an overview of the Schema-Guided Dialogue State Tracking task of the 8th
Dialogue System Technology Challenge. The goal of this task is to develop dialogue state …

Transformer models for mining intents and predicting activities from emails in knowledge-intensive processes

F Khandaker, A Senderovich, J Zhao, E Cohen… - … Applications of Artificial …, 2024 - Elsevier
Process mining is an interdisciplinary field that combines Artificial Intelligence and Business
Process Management to extract insights from historical event data. Knowledge-intensive …

Symbolic Dialogue for General Domain State Tracking

HN Quoc, TN Van, HP Trung, TN Quoc… - … Asian Conference on …, 2024 - ieeexplore.ieee.org
Task-oriented dialogue (TOD) systems are built to help users accomplish specific objectives.
However, even though ongoing reviews and improvements have been made to its …

A fast and robust bert-based dialogue state tracker for schema-guided dialogue dataset

V Noroozi, Y Zhang, E Bakhturina, T Kornuta - arxiv preprint arxiv …, 2020 - arxiv.org
Dialog State Tracking (DST) is one of the most crucial modules for goal-oriented dialogue
systems. In this paper, we introduce FastSGT (Fast Schema Guided Tracker), a fast and …

Choice fusion as knowledge for zero-shot dialogue state tracking

R Su, J Yang, TW Wu, BH Juang - ICASSP 2023-2023 IEEE …, 2023 - ieeexplore.ieee.org
With the demanding need for deploying dialogue systems in new domains with less cost,
zero-shot dialogue state tracking (DST), which tracks user's requirements in task-oriented …

Session-based recommendation with temporal convolutional network to balance numerical gaps

W Li, J Gou, Z Fan - Neurocomputing, 2022 - Elsevier
A session-based recommendation system recommends the next possible item for users by
learning the click session sequences of anonymous users. Considering the session data …

A multi-task bert model for schema-guided dialogue state tracking

E Kapelonis, E Georgiou, A Potamianos - arxiv preprint arxiv:2207.00828, 2022 - arxiv.org
Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to
successfully complete conversations. Recent state-of-the-art DST implementations rely on …

Sgd-qa: Fast schema-guided dialogue state tracking for unseen services

Y Zhang, V Noroozi, E Bakhturina… - arxiv preprint arxiv …, 2021 - arxiv.org
Dialogue state tracking is an essential part of goal-oriented dialogue systems, while most of
these state tracking models often fail to handle unseen services. In this paper, we propose …

HR-Agent: A Task-Oriented Dialogue (TOD) LLM Agent Tailored for HR Applications

W Xu, J Desai, F Wu, J Valvoda… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent LLM (Large Language Models) advancements benefit many fields such as
education and finance, but HR has hundreds of repetitive processes, such as access …