Towards Automatic Acquisition of a Fully Sense Tagged Corpus for Persian
AbstractSense tagged corpora play a crucial role in Natural Language Processing, particularly in Word Sense Disambiguation and Natural Language Understanding. Since semantic annotations are usually...
View ArticleFinding best evidence for evidence-based best practice recommendations in...
AbstractA major problem for Canadian health organizations is finding best evidence for evidence-based best practice recommendations. Medications are not always effectively used and misuse may harm...
View ArticleEfficient Bi-objective Team Formation in Social Networks
AbstractWe tackle the problem of finding a team of experts from a social network to complete a project that requires a set of skills. The social network is modeled as a graph. A node in the graph...
View ArticleRiding the tide of sentiment change: sentiment analysis with evolving online...
AbstractThe last decade has seen a rapid growth in the volume of online reviews. A great deal of research has been done in the area of opinion mining, aiming at analyzing the sentiments expressed in...
View ArticleTopic Modeling Using Collapsed Typed Dependency Relations
AbstractTopic modeling is a powerful tool to uncover hidden thematic structures of documents. Many conventional topic models represent documents as a bag-of-words, where the important linguistic...
View ArticleFinding top- $$k\, r$$ k r -cliques for keyword search from graphs in...
AbstractKeyword search over structured data offers an alternative method to explore and query databases for users that are not familiar with the structure of the data and/or a query language....
View ArticleOntology-Based Topic Labeling and Quality Prediction
AbstractProbabilistic topic models based on Latent Dirichlet Allocation (LDA) are increasingly used to discover hidden structure behind big text corpora. Although topic models are extremely useful...
View ArticleBuilding FP-Tree on the Fly: Single-Pass Frequent Itemset Mining
AbstractThe FP-Growth algorithm has been studied extensively in the field of frequent pattern mining. The algorithm offers the advantage of avoiding costly database scans in comparison with...
View ArticleComputational Role of Astrocytes in Bayesian Inference and Probability...
AbstractThe past few years have seen new research methods confirming more confidently that glia have a key information processing role in the brain, specifically in relation to learning capability....
View ArticleGeodesic and contour optimization using conformal mapping
AbstractWe propose a novel optimization algorithm for differentiable functions utilizing geodesics and contours under conformal mapping. The algorithm can locate multiple optima by first following a...
View ArticleMemory-adaptive high utility sequential pattern mining over data streams
AbstractHigh utility sequential pattern (HUSP) mining has emerged as an important topic in data mining. A number of studies have been conducted on mining HUSPs, but they are mainly intended for...
View ArticleContrast Pattern Based Collaborative Behavior Recommendation for Life...
AbstractPositive attitudes and happiness have major impacts on human health and in particular recovery from illness. While contributing factors leading human beings to positive emotional states are...
View ArticleMining significant high utility gene regulation sequential patterns
AbstractBackgroundMining frequent gene regulation sequential patterns in time course microarray datasets is an important mining task in bioinformatics. Although finding such patterns are of paramount...
View ArticleUsing Neural Network for Identifying Clickbaits in Online News Media
AbstractOnline news media sometimes use misleading headlines to lure users to open the news article. These catchy headlines that attract users but disappointed them at the end, are called clickbaits....
View ArticleDynamic Joint Variational Graph Autoencoders
AbstractLearning network representations is a fundamental task for many graph applications such as link prediction, node classification, graph clustering, and graph visualization. Many real-world...
View ArticleQuestion-Worthy Sentence Selection for Question Generation
Abstract The problem of automatic question generation from text is of increasing importance due to many useful applications. While deep neural networks achieved success in generating questions from...
View ArticleQuantification of Shape Properties and Their Effects on Particle Packing of...
AbstractParticle shape is known for its significant influence on the engineering properties of coarse grain soil. But it remains difficult to quantify how the different scales of shape properties will...
View ArticleA Novel Approach to Determining the Quality of News Headlines
AbstractHeadlines play a pivotal role in engaging and attracting news readers since headlines are the most visible parts of the news articles, especially in online media. Due to this importance, news...
View ArticleAdaptive Momentum Coefficient for Neural Network Optimization
AbstractWe propose a novel and efficient momentum-based first-order algorithm for optimizing neural networks which uses an adaptive coefficient for the momentum term. Our algorithm, called Adaptive...
View ArticleZipLine: an optimized algorithm for the elastic bulk synchronous parallel model
AbstractThe bulk synchronous parallel (BSP) is a celebrated synchronization model for general-purpose parallel computing that has successfully been employed for distributed training of deep learning...
View Article