Search

Abstract Topic modelling is a Natural Language Processing (NLP) technique that has gained popularity in the recent past. It identifies word co-occurrence patterns inside a document corpus to reveal hidden topics. Graph Neural Topic Model (GNTM) is a topic modelling technique that uses Graph Neural Networks (GNNs) to learn document representations effectively. It provides high-precision documents-topics and topics-words probability distributions. Such models find immense application in many sectors, including healthcare, financial services, and safety-critical systems like autonomous cars. This model is not explainable. As a matter of fact, the user cannot comprehend the underlying decision-making process. The paper introduces a technique to explain the documents-topics probability distributions output of GNTM. The explanation is achieved by building a local explainable model such as a probabilistic Naïve Bayes classifier. The experimental results using various benchmark NLP datasets show a fidelity of 88.39% between the predictions of GNTM and the local explainable model. This similarity implies that the proposed technique can effectively explain the documents-topics probability distribution output of GNTM.

Abstract In recent years, Native Language Identification (NLI) has shown significant interest in computational linguistics. NLI uses an author’s speech or writing in a second language to figure out their native language. This may find applications in forensic linguistics, language teaching, second language acquisition, authorship attribution, identification of spam emails or phishing websites, etc. Conventional pairwise string comparison techniques are computationally expensive and time-consuming. This paper presents fast NLI techniques based on string kernels such as spectrum, presence bits, and intersection string kernels incorporating different learners such as a Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting-XGBoost (XGB). Feature sets for the proposed techniques are generated using different combinations of features such as n-word grams and noun phrases. Experimental analyses are carried out using 8235 English as a second language articles from 10 different linguistic backgrounds from a typical NLP benchmark dataset. The experimental results show that the proposed NLI technique incorporating a spectrum string kernel with an RF classifier outperformed existing character n-gram string kernels incorporating SVM, RF, and XGB classifiers. Also, comparable results were observed among different combinations of string kernels. Interestingly, the random forest classifier outperformed SVM and XGB classifiers with different feature sets. All the proposed NLI techniques demonstrated promising results with significant improvement in training time, with the best result attaining more than a 95 percent decrease in training time. The reduced training time of proposed techniques makes it well suited to scale NLI applications for production.

The recent advancements in the Internet of Things (IoT) have engendered an increased penetration of cyber-physical systems such as internet-enabled devices and sensors for surveillance and management applications. This has posed an increased risk of attacks in these devices and networks by malevolent agents. Social Internet of Things (SIoT) is an emerging paradigm that incorporates the concept of Social Networking into the Internet of Things that paved the way to an area called Social Internet of Vehicles (SIoV) that is capable of autonomously establishing social relationships among other network participants for the overall system improvement. Due to the ad-hoc nature of the environment, it is hard to ensure the trustworthiness of the nodes to rely on the opinions, messages, and credibility of the message senders. We propose a Blockchain based reputation management system using Bayesian Inference approach for estimating the posterior probability of trustworthiness of each decision-making node in the network based on the decisions on incidents concerning the hypothesis. A dynamic weight learning mechanism of nodes and events is proposed for an efficient decision system. The proposed decision fusion algorithm is a novel voting mechanism based on the reputation of the node and the importance of the event. This approach uses Blockchain as a solution for identity management for node authorization and access control, and also for distributed storage of node reputation scores. The decision strategy of the proposed work outperforms other decision approaches such as simple majority voting, weighted voting, fuzzy rule-based inference, etc. The proposed approach out performs the state of the art trust management algorithms as discussed in results section, on the degree of punishment the propose algorithm offers to malicious activity. [ABSTRACT FROM AUTHOR]