Exploiting more associations between slots for multi-domain dialog state tracking

Bai, Hui; Yang, Yan; Wang, Jie

doi:10.26599/bdma.2021.9020013

Cited by 6 publications

(3 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Massive data generated in the IoT promotes vigorous development of big data, which is inevitably accompanied by threats and challenges to data and network security Bai et al (2022); . This section mainly discusses security issues and challenges of data and network.…”

Section: Concern Of Data and Network Securitymentioning

confidence: 99%

A survey of intelligent load monitoring in IoT-enabled distributed smart grids

Liu¹,

Gan²,

Zeng³

et al. 2023

IJAHUC

View full text Add to dashboard Cite

Power Load Monitoring has been a research hotspot since a few years ago. With development of artificial intelligence, construction of smart grid has become the most important part of power load monitoring. At the same time, task scheduling mechanism combined with the distributed IoT(Internet of Things) improves efficiency of smart grid. In this paper, applications of cloud/edge platform in the data acquisition, processing and scheduling of the IoT is introduced step by step, as well as applications and differences of artificial intelligence algorithm in each step, including Data Acquisition, Load Disaggregation, Load Forecasting and so on. Finally, combined with various optimization methods, future research directions are prospected, including data and network security issues, challenges faced by cloud/edge architecture, adaptive fine-grained Load Disaggregation, Load Forecasting.

show abstract

Section: Concern Of Data and Network Securitymentioning

confidence: 99%

A survey of intelligent load monitoring in IoT-enabled distributed smart grids

Liu¹,

Gan²,

Zeng³

et al. 2023

IJAHUC

View full text Add to dashboard Cite

show abstract

“…Several recent works addressing multi-domain DST have been shown to be successful (Bai et al, 2021). Specifically, Ren et al (2019) first determined the dialogue domains and slots and decoded their values, finally alleviating the computational difficulty of value decoding.…”

Section: Dialogue State Trackingmentioning

confidence: 99%

A Unified Dialogue Framework Based on Joint Generation of Dialogue Acts and Responses

Rong

et al. 2022

Preprint

View full text Add to dashboard Cite

Currently, building an end-to-end dialogue system for multi-domain task-oriented dialogue has some enormous challenges. Dialogue systems must obtain entire dialogue states from all relevant domains in order to respond correctly. However, multiple domains are involved in the actual dialogue process, which increases the difficulty of obtaining the dialogue state. In addition, dialogue systems process diverse information such as dialogue history, dialogue state, dialogue act, and database across domains, resulting in natural responses. These complex dialogue information brings greater difficulties to response generation. In this paper, we propose a novel unified dialogue framework for multi-domain dialogue in task-oriented dialog, including three modules: Encoder, Dialogue State Tracker and Multiple Decoders. First, encoder module encode all text input into continuous representations. Secondly, we train the dialogue state tracker module with a stacked-attention architecture.It learns information from slot-atten structure and domain-atten structure to track dialogue state. Then, multiple decoders module consists of act decoder structure and response decoder structure. It combines information from different textual inputs while modeling dialogue act. Finally, we jointly train all the above modules to generate system responses. We conducted extensive experiments on the dataset MultiWOZ. The experimental results show that our model achieves state-of-the-art results on evaluation metrics compared to models from previous work.

show abstract

“…Otherwise, the distribution of client data will be changed. In centralized machine learning ML [33][34][35] , autoencoders are used to overcome the unlabeled data problem. The idea of the process is to predict the labels of unlabeled data based on the labeled features, and then optimize the parameters by training the encoder and decoder to get the feature value closest to the original data.…”

Section: Introductionmentioning

confidence: 99%

ASCFL: Accurate and Speedy Semi-Supervised Clustering Federated Learning

Gong

Yang

et al. 2023

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

The influence of non-Independent Identically Distribution (non-IID) data on Federated Learning (FL) has been a serious concern. Clustered Federated Learning (CFL) is an emerging approach for reducing the impact of non-IID data, which employs the client similarity calculated by relevant metrics for clustering. Unfortunately, the existing CFL methods only pursue a single accuracy improvement, but ignore the convergence rate. Additionlly, the designed client selection strategy will affect the clustering results. Finally, traditional semi-supervised learning changes the distribution of data on clients, resulting in higher local costs and undesirable performance. In this paper, we propose a novel CFL method named ASCFL, which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data.To deal with unlabeled data, the prediction labels strategy predicts labels by encoders. The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round.What is more, the similarity-based clustering strategy uses a new indicator to measure the similarity between clients.Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets.

show abstract

Exploiting more associations between slots for multi-domain dialog state tracking

Cited by 6 publications

References 31 publications

A survey of intelligent load monitoring in IoT-enabled distributed smart grids

A survey of intelligent load monitoring in IoT-enabled distributed smart grids

A Unified Dialogue Framework Based on Joint Generation of Dialogue Acts and Responses

ASCFL: Accurate and Speedy Semi-Supervised Clustering Federated Learning

Contact Info

Product

Resources

About