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.

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.