Journal of Intelligent Information Systems最新文献

Argument pair extraction (APE) is a fine-grained task of argument mining which aims to identify arguments offered by different participants in some discourse and detect interaction relationships between arguments from different participants. In recent years, many research efforts have been devoted to dealing with APE in a multi-task learning framework. Although these approaches have achieved encouraging results, they still face several challenging issues. First, different types of sentence relationships as well as different levels of information exchange among sentences are largely ignored. Second, they solely model interactions between argument pairs either in an explicit or implicit strategy, while neglecting the complementary effect of the two strategies. In this paper, we propose a novel Mutually Enhanced Multi-Scale Relation-Aware Graph Convolutional Network (MMR-GCN) for APE. Specifically, we first design a multi-scale relation-aware graph aggregation module to explicitly model the complex relationships between review and rebuttal passage sentences. In addition, we propose a mutually enhancement transformer module to implicitly and interactively enhance representations of review and rebuttal passage sentences. We experimentally validate MMR-GCN by comparing with the state-of-the-art APE methods. Experimental results show that it considerably outperforms all baseline methods, and the relative performance improvement of MMR-GCN over the best performing baseline MRC-APE in terms of F1 score reaches to 3.48% and 4.43% on the two benchmark datasets, respectively.

Hiring knowledgeable and cost-effective individuals, who use their knowledge and expertise to boost the organization, is extremely important for organizations as they are the most valuable assets. T-shaped experts are the best option based on agile methodology. The T-shaped professional has a deep understanding of one topic and broad knowledge of several others. Compared to other types of professionals, T-shaped professionals are better communicators and cheaper to hire. Finding T-shaped experts in a given skill area requires determining each candidate’s depth of knowledge and shape of expertise. To estimate each candidate’s depth of knowledge in a given skill area, we propose a translation-based method that utilizes two attention-based skill translation models to overcome the vocabulary mismatch between skills and user documents. We also propose two new approaches based on binary cross-entropy and focal loss to determine whether each user is T-shaped. Our experiments on three collections of the StackOverflow dataset demonstrate the efficiency of our proposed method compared to the state-of-the-art approaches.

({{textbf{Latent}}varvec{Out}}) is a recently introduced algorithm for unsupervised anomaly detection which enhances latent space-based neural methods, namely (Variational) Autoencoders, GANomaly and ANOGan architectures. The main idea behind it is to exploit both the latent space and the baseline score of these architectures in order to provide a refined anomaly score performing density estimation in the augmented latent-space/baseline-score feature space. In this paper we investigate the performance of ({{textbf{Latent}}varvec{Out}}) acting as a one-class classifier and we experiment the combination of ({{textbf{Latent}}varvec{Out}}) with GAAL architectures, a novel type of Generative Adversarial Networks for unsupervised anomaly detection. Moreover, we show that the feature space induced by ({{textbf{Latent}}varvec{Out}}) has the characteristic to enhance the separation between normal and anomalous data. Indeed, we prove that standard data mining outlier detection methods perform better when applied on this novel augmented latent space rather than on the original data space.

Geomagnetic activities have a crucial impact on Earth, which can affect spacecraft and electrical power grids. Geospace scientists use a geomagnetic index, called the Kp index, to describe the overall level of geomagnetic activity. This index is an important indicator of disturbances in the Earth’s magnetic field and is used by the U.S. Space Weather Prediction Center as an alert and warning service for users who may be affected by the disturbances. Another commonly used index, called the ap index, is converted from the Kp index. Early and accurate prediction of the Kp and ap indices is essential for preparedness and disaster risk management. In this paper, we present a deep learning framework, named GNet, to perform short-term forecasting of the Kp and ap indices. Specifically, GNet takes as input time series of solar wind parameters’ values, provided by NASA’s Space Science Data Coordinated Archive, and predicts as output the Kp and ap indices respectively at time point (varvec{t + w}) hours for a given time point (varvec{t}) where (varvec{w}) ranges from 1 to 9. GNet combines transformer encoder blocks with Bayesian inference, which is capable of quantifying both aleatoric uncertainty (data uncertainty) and epistemic uncertainty (model uncertainty) in making predictions. Experimental results show that GNet outperforms closely related machine learning methods in terms of the root mean square error and R-squared score. Furthermore, GNet can provide both data and model uncertainty quantification results, which the existing methods cannot offer. To our knowledge, this is the first time that Bayesian transformers have been used for geomagnetic activity prediction.