Search results

Intent detection and slot filling are two important tasks in question comprehension of a question answering system. This study aims to build a joint task model with some generalization ability and benchmark its performance over other neural network models mentioned in this paper.

This study used a deep-learning-based approach for the joint modeling of question intent detection and slot filling. Meanwhile, the internal cell structure of the long short-term memory (LSTM) network was improved. Furthermore, the dataset Computer Science Literature Question (CSLQ) was constructed based on the Science and Technology Knowledge Graph. The datasets Airline Travel Information Systems, Snips (a natural language processing dataset of the consumer intent engine collected by Snips) and CSLQ were used for the empirical analysis. The accuracy of intent detection and F1 score of slot filling, as well as the semantic accuracy of sentences, were compared for several models.

The results showed that the proposed model outperformed all other benchmark methods, especially for the CSLQ dataset. This proves that the design of this study improved the comprehensive performance and generalization ability of the model to some extent.

This study contributes to the understanding of question sentences in a specific domain. LSTM was improved, and a computer literature domain dataset was constructed herein. This will lay the data and model foundation for the future construction of a computer literature question answering system.

Recently, deep learning (DL) has been widely applied in various aspects of human endeavors. However, studies have shown that DL models may also be a primary cause of data leakage, which raises new data privacy concerns. Membership inference attacks (MIAs) are prominent threats to user privacy from DL model training data, as attackers investigate whether specific data samples exist in the training data of a target model. Therefore, the aim of this study is to develop a method for defending against MIAs and protecting data privacy.

One possible solution is to propose an MIA defense method that involves adjusting the model’s output by mapping the output to a distribution with equal probability density. This approach effectively preserves the accuracy of classification predictions while simultaneously preventing attackers from identifying the training data.

Experiments demonstrate that the proposed defense method is effective in reducing the classification accuracy of MIAs to below 50%. Because MIAs are viewed as a binary classification model, the proposed method effectively prevents privacy leakage and improves data privacy protection.

The method is only designed to defend against MIA in black-box classification models.

The proposed MIA defense method is effective and has a low cost. Therefore, the method enables us to protect data privacy without incurring significant additional expenses.

This paper aims to provide a typical example of accounting for the carbon dioxide equivalent (CO₂e) in underdeveloped cities, especially for the Poyang Lake area in China. The accounting can increase public understanding and trust in climate mitigation strategies by showing more detailed data.

The paper uses the “Global Protocol for Community-scale greenhouse gas emission inventories (GPC)” method, a worldwide comparable framework for calculating urban CO₂e emission (CE). The empirical case is an underdeveloped city, Nanchang, in China.

The results show the total CE of Nanchang, containing the electricity CE of Scope 2, grew rapidly from 12.49 Mt in 1994 to 55.00 Mt in 2014, with the only recession caused by the global financial crisis in 2008. The biggest three contributors were industrial energy consumption, transportation and industrial processes, which contributed 44.71-72.06, 4.10-25.07 and 9.07-22.28 per cent, respectively, to the total CE. Almost always, more than 74.41 per cent of Nanchang’s CE was related to coal. When considering only the CEs from coal, oil and gas, these CEs per unit area of Nanchang were always greater than those of China and the world. Similarly, these CEs per gross domestic product of Nanchang were always bigger than those of the world. Thus, based on these conclusions, some specific countermeasures were recommended.

This paper argues that the CO₂e accounting of underdeveloped cities by using the GPC framework should be promoted when designing climate mitigation policies. They can provide more scientific data to justify related countermeasures.

With the evolution of the turbulent environment constantly triggering the emergence of a trust crisis between organizations, how can university–industry (U–I) alliances respond to the trust crisis when conducting green technology innovation (GTI) activities? This paper aims to address this issue.

The authors examined the process of trust crisis damage, including trust first suffering instantaneous impair as well as subsequently indirectly affecting GTI level, and ultimately hurting the profitability of green innovations. In this paper, a piecewise deterministic dynamic model is deployed to portray the trust and the GTI levels in GTI activities of U–I alliances.

The authors analyze the equilibrium results under decentralized and centralized decision-making modes to obtain the following conclusions: Trust levels are affected by a combination of hazard and damage (short and long term) rates, shifting from steady growth to decline in the presence of low hazard and damage rates. However, the GTI level has been growing steadily. It is essential to consider factors such as the hazard rate, the damage rate in the short and long terms, and the change in marginal profit in determining whether to pursue an efficiency- or recovery-friendly strategy in the face of a trust crisis. The authors found that two approaches can mitigate trust crisis losses: implementing a centralized decision-making mode (i.e. shared governance) and reducing pre-crisis trust-building investments. This study offers several insights for businesses and academics to respond to a trust crisis.

The present research can be extended in several directions. Instead of distinguishing attribution of trust crisis, the authors use hazard rate, short- and long-term damage rates and change in marginal profitability to distinguish the scale of trust crises. Future scholars can further add an attribution approach to enrich the classification of trust crises. Moreover, the authors only consider trust crises because of unexpected events in a turbulent environment; in fact, a trust crisis may also be a plateauing process, yet the authors do not study this situation.

First, the authors explore what factors affect the level of trust and the level of GTI when a trust crisis occurs. Second, the authors provide guidelines on how businesses and academics can coordinate their trust-building and GTI efforts when faced with a trust crisis in a turbulent environment.

First, the interaction between psychology and innovation management is explored in this paper. Although empirical studies have shown that trust in U–I alliances is related to innovation performance, and scholars have developed differential game models to portray the GTI process, building a differential game model to explore such an interaction is still scarce. Second, the authors incorporate inter-organizational trust level into the GTI level in university–industry collaboration, applying differential equations to portray the trust building and GTI processes, respectively, to reveal the importance of trust in CTI activities. Third, the authors establish a piecewise deterministic dynamic game model wherein the impact of crisis shocks is not equal to zero, which is inconsistent with most previous studies of Brownian motion.

The purpose of this paper is to explore the relationship of fluid flow and heat transfer inside the generator, a large hydro-generator is taken for an example and the temperature field in the generator is calculated according to computation of fluid field by using of corresponding mathematics methods based on fluid mechanical theory and heat transfer theory.

To calculate the temperature field of the generator more accurately, a large-scale hydro-generator is taken as an example and the mathematical model and physical model of 3D stator temperature field and fluid field are established. And the calculation results of the fluid field are applied into the physics field of generator, coupled relationship between fluid field and temperature field was calculated by using of finite volume method and finite element method, respectively. The temperature fields based on fluid fields and the effect of different fluid flow state on generator temperature were analyzed and compared.

The calculated results shows show good agreement with the measured results, meanwhile the effect of different fluid field state on the temperature field is analyzed and the relationship between temperature fields and fluid fields is achieved, which will provide a theoretical basis for ventilation structure design and calculation of synthesis physical fields.

The relationship between temperature fields and fluid fields is obtained, providing a theoretical basis for ventilation structure design and calculation of synthesis physical fields.