Considering city road environment as the background, by researching GPSR greedy algorithm and the movement characteristics of vehicle nodes in VANET, this paper proposes the concept of circle ...changing trends angle in vehicle speed fluctuation curve and the movement domain and designs an SWF routing algorithm based on the vehicle speed point forecasted and the changing trends time computation. Simulation experiments are carried out through using a combination of NS-2 and VanetMobiSim software. Compared with the performance of the SWF-GPSR protocol with general GPSR, 2-hop C-GEDIR, and the GRA and AODV protocols, we find that the SWF algorithm has a certain degree of improvement in routing hops, the packet delivery ratio, delay performance, and link stability.
This paper constructs a kind of spread willingness computing based on information dissemination model for social network. The model takes into account the impact of node degree and dissemination ...mechanism, combined with the complex network theory and dynamics of infectious diseases, and further establishes the dynamical evolution equations. Equations characterize the evolutionary relationship between different types of nodes with time. The spread willingness computing contains three factors which have impact on user’s spread behavior: strength of the relationship between the nodes, views identity, and frequency of contact. Simulation results show that different degrees of nodes show the same trend in the network, and even if the degree of node is very small, there is likelihood of a large area of information dissemination. The weaker the relationship between nodes, the higher probability of views selection and the higher the frequency of contact with information so that information spreads rapidly and leads to a wide range of dissemination. As the dissemination probability and immune probability change, the speed of information dissemination is also changing accordingly. The studies meet social networking features and can help to master the behavior of users and understand and analyze characteristics of information dissemination in social network.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Internet of Things (IoT) is regarded as a remarkable development of the modern information technology. There is abundant digital products data on the IoT, linking with multiple types of ...objects/entities. Those associated entities carry rich information and usually in the form of query records. Therefore, constructing high quality topic hierarchies that can capture the term distribution of each product record enables us to better understand users’ search intent and benefits tasks such as taxonomy construction, recommendation systems, and other communications solutions for the future IoT. In this paper, we propose a novel record entity topic model (RETM) for IoT environment that is associated with a set of entities and records and a Gibbs sampling-based algorithm is proposed to learn the model. We conduct extensive experiments on real-world datasets and compare our approach with existing methods to demonstrate the advantage of our approach.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
Intent detection and slot filling are two important tasks for spoken language understanding. Considering the close relation between them, most existing methods joint them by sharing parameters or ...establishing explicit connection between them for potentially benefiting each other. However, most of them only consider single directional connection and ignore their cross-impact between them. Moreover, these joint methods treat the predicted labels as the gold labels, which may cause error propagation. In this paper, we propose a two-stage Graph Attention Interactive Refine (GAIR) framework. In stage one, the basic SLU model predicts the coarse intent and slots. In stage two, we select the top-k candidate labels from stage one and construct a graph to make full advantage of intent and slot filling information. By constructing such graph, our framework can establish a bidirectional connection between two tasks and refine the coarse result, which can better take full use of cross-impact between two tasks. Moreover, contextual regularization is introduced for better alleviating error propagation. Experiments on two datasets show that our model achieves the state-of-the-arts performance.
•Reverse saturable absorption effect of real saturable absorber on conventional and dissipative solitons is investigated.•Reverse saturable absorption effect clamps peak power of conventional and ...dissipative solitons.•Revealing the role of reverse saturable absorption effect in different mode-locked regimes.
We numerically investigate the influence of the reverse saturable absorption effect of real saturable absorbers on conventional and dissipative solitons. The results show that the reverse saturable absorption effect leads to more loss and clamps peak power of both conventional and dissipative solitons, but plays different roles on their properties. When the cavity operates at conventional solitons state, the reverse saturable absorption effect restricts the maximum pulse energy to less than 0.1 nJ, facilitates the formation of multiple solitons, but maintains the time-bandwidth product close to 0.315, indicating the pulses maintain the sech2 shape. While the cavity operates at dissipative solitons state, the reverse saturable absorption effect increases the maximum pulse energy from 11 to 13 nJ and plays a key role in transforming the pulse states, which further facilitates the generation of dissipative soliton resonance pulses. In addition, the reason of the different influences on pulses in two mode-locked regimes is also discussed. Our results reveal the role and promote the rational use of the reverse saturable absorption effect in different mode-locked regimes.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
This research signifies a considerable breakthrough in leveraging Large Language Models (LLMs) for multi-intent spoken language understanding (SLU). Our approach re-imagines the use of entity slots ...in multi-intent SLU applications, making the most of the generative potential of LLMs within the SLU landscape, leading to the development of the EN-LLM series. Furthermore, we introduce the concept of Sub-Intent Instruction (SII) to amplify the analysis and interpretation of complex, multi-intent communications, which further supports the creation of the ENSI-LLM models series. Our novel datasets, identified as LM-MixATIS and LM-MixSNIPS, are synthesized from existing benchmarks. The study evidences that LLMs may match or even surpass the performance of the current best multi-intent SLU models. We also scrutinize the performance of LLMs across a spectrum of intent configurations and dataset distributions. On top of this, we present two revolutionary metrics - Entity Slot Accuracy (ESA) and Combined Semantic Accuracy (CSA) - to facilitate a detailed assessment of LLM competence in this multifaceted field." Our code and datasets are available at \url{https://github.com/SJY8460/SLM}.
Chinese Text Error Correction (CTEC) aims to detect and correct errors in the input text, which benefits human daily life and various downstream tasks. Recent approaches mainly employ Pre-trained ...Language Models (PLMs) to resolve CTEC. Although PLMs have achieved remarkable success in CTEC, we argue that previous studies still overlook the importance of human thinking patterns. To enhance the development of PLMs for CTEC, inspired by humans' daily error-correcting behavior, we propose a novel model-agnostic progressive learning framework, named ProTEC, which guides PLMs-based CTEC models to learn to correct like humans. During the training process, ProTEC guides the model to learn text error correction by incorporating these sub-tasks into a progressive paradigm. During the inference process, the model completes these sub-tasks in turn to generate the correction results. Extensive experiments and detailed analyses demonstrate the effectiveness and efficiency of our proposed model-agnostic ProTEC framework.
Recently, the development and progress of Large Language Models (LLMs) have amazed the entire Artificial Intelligence community. Benefiting from their emergent abilities, LLMs have attracted more and ...more researchers to study their capabilities and performance on various downstream Natural Language Processing (NLP) tasks. While marveling at LLMs' incredible performance on all kinds of tasks, we notice that they also have excellent multilingual processing capabilities, such as Chinese. To explore the Chinese processing ability of LLMs, we focus on Chinese Text Correction, a fundamental and challenging Chinese NLP task. Specifically, we evaluate various representative LLMs on the Chinese Grammatical Error Correction (CGEC) and Chinese Spelling Check (CSC) tasks, which are two main Chinese Text Correction scenarios. Additionally, we also fine-tune LLMs for Chinese Text Correction to better observe the potential capabilities of LLMs. From extensive analyses and comparisons with previous state-of-the-art small models, we empirically find that the LLMs currently have both amazing performance and unsatisfactory behavior for Chinese Text Correction. We believe our findings will promote the landing and application of LLMs in the Chinese NLP community.
In recent years, Chinese Spelling Check (CSC) has been greatly improved by designing task-specific pre-training methods or introducing auxiliary tasks, which mostly solve this task in an end-to-end ...fashion. In this paper, we propose to decompose the CSC workflow into detection, reasoning, and searching subtasks so that the rich external knowledge about the Chinese language can be leveraged more directly and efficiently. Specifically, we design a plug-and-play detection-and-reasoning module that is compatible with existing SOTA non-autoregressive CSC models to further boost their performance. We find that the detection-and-reasoning module trained for one model can also benefit other models. We also study the primary interpretability provided by the task decomposition. Extensive experiments and detailed analyses demonstrate the effectiveness and competitiveness of the proposed module.
Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in given sentences. Recently, multi-domain CSC has gradually attracted the attention of researchers because it is more ...practicable. In this paper, we focus on the key flaw of the CSC model when adapting to multi-domain scenarios: the tendency to forget previously acquired knowledge upon learning new domain-specific knowledge (i.e., catastrophic forgetting). To address this, we propose a novel model-agnostic Multi-stage Knowledge Transfer (MKT) framework, which utilizes a continuously evolving teacher model for knowledge transfer in each domain, rather than focusing solely on new domain knowledge. It deserves to be mentioned that we are the first to apply continual learning methods to the multi-domain CSC task. Experiments prove the effectiveness of our proposed method, and further analyses demonstrate the importance of overcoming catastrophic forgetting for improving the model performance.
PDF
