Galaxy: A generative pre-trained model for task-oriented dialog with semi-supervised learning and explicit policy injection
Pre-trained models have proved to be powerful in enhancing task-oriented dialog systems.
However, current pre-training methods mainly focus on enhancing dialog understanding …
However, current pre-training methods mainly focus on enhancing dialog understanding …
Unified dialog model pre-training for task-oriented dialog understanding and generation
Recently, pre-training methods have shown remarkable success in task-oriented dialog
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …
Knowledge grounded medical dialogue generation using augmented graphs
Smart healthcare systems that make use of abundant health data can improve access to
healthcare services, reduce medical costs and provide consistently high-quality patient care …
healthcare services, reduce medical costs and provide consistently high-quality patient care …
Diverse dialogue generation by fusing mutual persona-aware and self-transferrer
In recent years, personalized dialogue generation has attracted researchers' attention due to
its wide range of applications. Although there has been much excellent research, current …
its wide range of applications. Although there has been much excellent research, current …
Multitask learning for acoustic scene classification with topic-based soft labels and a mutual attention mechanism
Y Leng, J Zhuang, J Pan, C Sun - Knowledge-Based Systems, 2023 - Elsevier
Acoustic scene classification (ASC) is a fundamental task of computational sound scene
analysis that aims to identify the acoustic environment via audio. Many multitask learning …
analysis that aims to identify the acoustic environment via audio. Many multitask learning …
Adversarial learning-based multi-level dense-transmission knowledge distillation for AP-ROP detection
H Xie, Y Liu, H Lei, T Song, G Yue, Y Du, T Wang… - Medical Image …, 2023 - Elsevier
Abstract The Aggressive Posterior Retinopathy of Prematurity (AP-ROP) is the major cause
of blindness for premature infants. The automatic diagnosis method has become an …
of blindness for premature infants. The automatic diagnosis method has become an …
Heterogeneous relational graph neural networks with adaptive objective for end-to-end task-oriented dialogue
End-to-end task-oriented dialogue systems, which provide a natural and informative way for
human–computer interaction, are gaining more and more attention. The main challenge of …
human–computer interaction, are gaining more and more attention. The main challenge of …
Space-3: Unified dialog model pre-training for task-oriented dialog understanding and generation
Recently, pre-training methods have shown remarkable success in task-oriented dialog
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …
(TOD) systems. However, most existing pre-trained models for TOD focus on either dialog …
Selective policy transfer in multi-agent systems with sparse interactions
Previously trained single-agent strategies, which are considerably easier to acquire than
multi-agent strategies, are instructive for multi-agent reinforcement learning, especially when …
multi-agent strategies, are instructive for multi-agent reinforcement learning, especially when …
Exploring auxiliary reasoning tasks for task-oriented dialog systems with meta cooperative learning
In this paper, we propose a Meta Cooperative Learning (MCL) framework for task-oriented
dialog systems (TDSs). Our model consists of an auxiliary KB reasoning task for learning …
dialog systems (TDSs). Our model consists of an auxiliary KB reasoning task for learning …