Abstract:This paper designs a dialogue model based on the granulated knowledge graph (Granulation Knowledge aware Dialogue Model, GKDM). Through the method of structural granulation, the knowledge graph is divided into two modules: local knowledge graph and non-local knowledge graph, respectively capturing the local semantics adjacent to the knowledge entity and the overall semantic representation of the located knowledge sub-graph, which solves the problem of the division of the knowledge graph. This paper designs the static graph attention mechanism and the hierarchical dynamic graph attention mechanism to participate in the process of encoding and decoding in the model respectively, and aggregates the semantics of knowledge entities through multi-level attention weights, and fuses them into the text vector, which solves the problem of the fusion of multi-layer knowledge information. Based on the above two innovations, the model proposed in this paper alleviates the problems of the current knowledge graph-based dialogue model that cannot capture the reasoning meaning of the multi-hop paths of the knowledge graph and the inconsistent theme of the reply context.

Alert Name:
Alerting to:
Authentication email will be sent to your email address in 24 hours
Frequency:
Email Message Format:	Plain text Graphical(HTML)

Complete the form below and we will recommend the selected titles to your friends on your behalf. * Indicates a required field.
Your name*:
Your email address*:
Recipient's name*:
Recipient's email address*:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find the page(s) useful.

Your name:
Your email address:
Recipient's name:
Recipient's email address:
(multiple recipient's names and email addresses should be separated with semicolons)
Your comments:	I thought you would find this page useful.

Disclaimer: This message was sent to your friend using the "Send it to a friend" facility on the Sciencepaper Online’ WWW site, http://www.paper.edu.cn/en. The Sciencepaper Online is not responsible for the content of this email, and anything said in this email does not necessarily reflect the Sciencepaper Online's views.


	1. Granularized Dialogue Model of The Knowledge Graph
	,
	Computer Science and Technology 10 April 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:This paper designs a dialogue model based on the granulated knowledge graph (Granulation Knowledge aware Dialogue Model, GKDM). Through the method of structural granulation, the knowledge graph is divided into two modules: local knowledge graph and non-local knowledge graph, respectively capturing the local semantics adjacent to the knowledge entity and the overall semantic representation of the located knowledge sub-graph, which solves the problem of the division of the knowledge graph. This paper designs the static graph attention mechanism and the hierarchical dynamic graph attention mechanism to participate in the process of encoding and decoding in the model respectively, and aggregates the semantics of knowledge entities through multi-level attention weights, and fuses them into the text vector, which solves the problem of the fusion of multi-layer knowledge information. Based on the above two innovations, the model proposed in this paper alleviates the problems of the current knowledge graph-based dialogue model that cannot capture the reasoning meaning of the multi-hop paths of the knowledge graph and the inconsistent theme of the reply context.
	TO cite this article:,. Granularized Dialogue Model of The Knowledge Graph[OL].[10 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763289


	2. Research on Lightweight Based on HiFi-GAN Model
	,
	Electrics, Communication and Autocontrol Technology 08 April 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:The HiFi-GAN model combines audio with high efficiency and high fidelity in speech synthesis, but its huge model parameters and calculations make it difficult to store, deploy, and perform real-time computing on limited-resource devices. There are relatively few studies on the compression and acceleration of HiFi-GAN models, while the need for real-time speech synthesis on mobile devices and edge devices is very extensive. This paper studies the lightweighting method of HiFi-GAN model to realize the network compression and deploy on the hardware platform. The main research and results of the paper are as follows: Aiming at the problems of high computing and storage resource consumption and complex structure in the inference stage of HiFi-GAN, this paper proposes a compression method combining knowledge distillation and architecture search according to its network structure. In this method, the resBlock layer of the HiFi-GAN model is convolutional decomposed to obtain a relatively compact student model, and the designed training objective scheme is used for distillation learning. After that, this student network is used as a "one-time" network for architecture search, and finally the compact optimal sub-student model is obtained. Experiments show that this method significantly compreses the size of the HiFi-GAN model and reduces the amount of computation, and generates good speech quality PESQ values on both the single speaker LJSpeech dataset and the unknown speaker VCTK dataset.
	TO cite this article:,. Research on Lightweight Based on HiFi-GAN Model[OL].[ 8 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763318

Saved Papers

Saved Papers


	3. Study on Optimization of Zinc Anode Performance with 2-mercaptosuccinic Acid Electrolyte Additive
	,
	Chemical Engineering 08 April 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:Adding additives to the electrolyte is an effective and simple method to improve the electrochemical performance of zinc anodes. In this paper, 2-mercaptosuccinic acid (MA) is introduced into the ZnSO4 electrolyte as an additive to improve the zinc anode performance. Electrochemical tests show that the addition of MA additive can reduce the charge transfer resistance of the interface, reduce the occurrence of side reactions such as hydrogen evolution and corrosion, reduce the nucleation overpotential, which is beneficial to the uniform nucleation of zinc, constrain the diffusion of zinc ions and accelerate the migration of zinc ions, which is beneficial to the uniform deposition of zinc and inhibits dendrite growth. Through XRD and SEM characterization, it was found that there was no obvious by-product generation on the surface of the zinc anode, and the zinc foil was protected. The Zn\|\|Zn batteries containing MA additive electrolyte shows excellent long-term cycle performance. It can cycle stably for 1574 h under the conditions of 5 mA/cm2, 1 mAh/cm2, and has a large current density and area of 8 mA/cm2, 5 mAh/cm2. It can cycle stably for 546 hours even if the capacity is high. The polarization voltage during the cycle is low, showing excellent cycle stability. This shows that it is feasible to choose 2-mercaptosuccinic acid (MA) as an electrolyte additive to improve the stability of the zinc anode.
	TO cite this article:,. Study on Optimization of Zinc Anode Performance with 2-mercaptosuccinic Acid Electrolyte Additive[OL].[ 8 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763269


	4. Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval
	,,,,
	Computer Science and Technology 02 April 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:This study focuses on weakly-supervised Video Moment Retrieval (VMR), aiming to identify a moment semantically similar to the given query within an untrimmed video using only video-level correspondences, without relying on temporal annotations during training. Previous methods either aggregate predictions for all instances in the video, or indirectly address the task by proposing reconstructions for the query. However, these methods often produce low-quality temporal proposals, struggle with distinguishing misaligned moments in the same video, or lack stability due to a reliance on a single auxiliary task.To address these limitations, we present a novel weakly-supervised method called Multi-proposal Collaboration and Multi-task Training (MCMT). Initially, we generate multiple proposals and derive corresponding learnable Gaussian masks from them. These masks are then combined to create a high-quality positive sample mask, highlighting video clips most relevant to the query. Concurrently, we classify other clips in the same video as easy negative sample and the entire video as hard negative sample. During training, we introduce forward and inverse masked query reconstruction tasks to impose more substantial constraints on the network, promoting more robust and stable retrieval performance. Extensive experiments on two standard benchmarks affirm the effectiveness of the proposed method in VMR.
	TO cite this article:,,, et al. Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval[OL].[ 2 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763143


	5. Buyang-Huanwu decoction blocks TGF-β/Smad pathway by inhibiting FUT8 expression in IRI mice
	,,,,,,,
	Traditional Chinese Medicine and Pharmacology 02 April 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract: In order to elucidate the mechanism of Buyang-Huanwu decoction in TGF-β/Smad signaling pathway in AKI-to-CKD mice. We constructed animal model of AKI-to-CKD by renal ischemia-reperfusion injury (IRI). We grouped the mice, assessed renal function on the 30th day after modeling, tested the level of α-SMA and TGF-β/Smad pathways, and detected the changes of Fut8 and VEGF R2 levels and core fucosylation of TGF-βRⅡ. The results show that Buyang-Huanwu decoction also down-regulates the level of Fut8 and core fucosylation of TGF-βRII, up-regulates the level of VEGF R2, inhibits the activation of TGF-β/Smad, and eases the process of IRI. These data indicate that Buyang-Huanwu decoction could inhibit the activation of TGF-β/Smad pathway by inhibiting the Fut8 and then block the pathological process of AKI-to-CKD.
	TO cite this article:,,, et al. Buyang-Huanwu decoction blocks TGF-β/Smad pathway by inhibiting FUT8 expression in IRI mice[OL].[ 2 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4762419


	6. Evolution of magnetization textures in Mn1.4PtSn under magnetic field
	,,,,
	Physics 01 April 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:In this study, we used Lorentz transmission electron microscopy (LTEM) and the transport of intensity equation (TIE) method to investigate the spin structures in the Mn1.4PtSn magnet, which exhibits D2d symmetry. Our goal was to observe how these spin structures evolve under the influence of an external magnetic field. In particular, the application of a perpendicular field was able to modulate the stripe domain widths and induce the formation of anti-skyrmions. While an in-plane magnetic field can control the state of these anti-skyrmions, the coexistence of different skyrmions suggests that the hysteresis properties of the magnet may affect the effectiveness of the field control.
	TO cite this article:,,, et al. Evolution of magnetization textures in Mn1.4PtSn under magnetic field[OL].[ 1 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4762933


	7. Stability and convergence of a consistent splitting GSAV scheme for the the time-dependent thermally coupledmagnetohydrodynamics equations
	,
	Mathematics 29 March 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:The paper mainly considers and analyzes the first order, linear and fully-decoupled numerical schemefor the time-dependent incompressible thermally coupled magnetohydrodynamic equations.Firstly, an equivalent system of the original problem is formed by introducing the suitable generalizedscalar auxiliary variable, the consist splitting method is employed to construct the ideal numerical scheme.Then, a series of linear algebra equations with the constant coefficients at each time step.As a consequence, the computational size is reduces and the computational cost is saved.Secondly, the unconditional stability results of numerical solutions are established by the energy methodand the recursive analysis method. Finally, the convergence results of numerical approximations are presented by introducing the Stokes pressure and using the mathematical induction method
	TO cite this article:,. Stability and convergence of a consistent splitting GSAV scheme for the the time-dependent thermally coupledmagnetohydrodynamics equations[OL].[29 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762954


	8. The Analysis of Adversarial Robustness in Federated Learning Based on Differential Privacy
	,
	Computer Science and Technology 26 March 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:Federated learning (FL) allows multiple participants to train models collaboratively by keeping their data local while exchanging updates, however, this also increases the risk of attack. Models in FL are as vulnerable as centrally trained models against adversarial examples. And with frequent data exchanging, the risk of data breaches increases. To enhance the robustness against adversarial examples, this paper introduces the differential privacy into FL, which is also an effective mechanism used for privacy protection.Many popular approaches that involve adversarial training in FL often compromise test accuracy while effect. In this work, a novel method is proposed which applies differential privacy to enhance both adversarial robustness and privacy protection level. Extensive experiments on multiple datasets demonstrate the proposed approach has a better performance compared with other baselines.
	TO cite this article:,. The Analysis of Adversarial Robustness in Federated Learning Based on Differential Privacy[OL].[26 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4763096


	9. Defect-correction variational multiscale methods for the stationary incompressible magnetohydrodynamics flow
	,
	Mathematics 25 March 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:In this paper, the defect correction variational multiscale method (DCVMM) based on local Gauss integrations is developed for the stationary incompressible magnetohydrodynamics (MHD) problem. Firstly, we review the variational multiscale method (VMM) for solving the stationary incompressible magnetohydrodynamics problem, and give the stability and convergence of the numerical solutions. Sencondly, the DCVMM based on local Gauss integrations is developed for the stationary incompressible MHD problem, and the stability and optimal error results of the numerical solutions are established. Finally, some numerical examples are provided to indicate with the obtained theoretical findings and show the performances of the considered numerical schemes.
	TO cite this article:,. Defect-correction variational multiscale methods for the stationary incompressible magnetohydrodynamics flow[OL].[25 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762956


	10. GPALzz: A state-leading fuzzing framework via basic network communication interface
	,
	Computer Science and Technology 25 March 2024
	Show/Hide Abstract \| Cite this paper�Full-text: PDF (0 KB)

	Abstract:Today, the rapid adoption of IoT devices has brought security risks while facilitating people's lives. Latest research focuses on information acquisition and state establishment, however exists the defects of relys on vendors and lacks universality; focuses on communication formats rather than device information; difficult to accurately guide fuzzing into specific states then in a stable state. To address the above issues, we propose an interactive leading fuzzing scheme, named GPALzz. It uses active automata learning to break free from vendor dependence, establishes device service state guidance fuzzy testing, and utilies interaction capabilities to establish an equivalent automaton that describes device service state information. Furthermore, we selected 9 devices to verify our scheme and discovered 24 crashes in 7 devices.
	TO cite this article:,. GPALzz: A state-leading fuzzing framework via basic network communication interface[OL].[25 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762868

	Check out RSS, or use RSS reader to subscribe this item