Using the technique of semantic mirroring a graph is obtained that represents words and their translations from a parallel corpus or a bilingual lexicon. The connectedness of the graph holds information about the semantic relations of words that occur in the translations. Spectral graph theory is used to partition the graph, which leads to a grouping of the words in different clusters. We illus...

Many real-world networks have a rich collection of objects. The semantics of these objects allows us to capture different classes of proximities, thus enabling an important task of semantic proximity search. As the core of semantic proximity search, we have to measure the proximity on a heterogeneous graph, whose nodes are various types of objects. Most of the existing methods rely on engineeri...

Inferring semantic relevance among entities (e.g., entries of Wikipedia) is important and challenging. According to the information resources, the inference can be categorized into learning with either raw text data, or labeled text data (e.g., wiki page), or graph knowledge (e.g, WordNet). Although graph knowledge tends to be more reliable, text data is much less costly and offers a better cov...

Querying large RDF spaces with traditional query languages such as SPARQL is challenging as it requires a familiarity with the structure of the RDF graph and the names (URIs) of its classes, properties and relevant individuals. In this paper, we propose a complementary approach based on Vector Space Models (VSM), more concretely Random Indexing (RI) [1] for building a semantic index for a large...

Graph Contrastive Learning (GCL) has recently drawn much research interest for learning generalizable node representations in a self-supervised manner. In general, the contrastive process GCL is performed on top of learned by graph neural network (GNN) backbone, which transforms and propagates contextual information based its local neighborhoods. However, nodes sharing similar characteristics m...

The performances of semisupervised clustering for unlabeled data are often superior to those unsupervised learning, which indicates that semantic information attached clusters can significantly improve feature representation capability. In a graph convolutional network (GCN), each node contains about itself and its neighbors is beneficial common unique features among samples. Combining these fi...

Building façades can feature different patterns depending on the architectural style, functionality, and size of buildings; therefore, reconstructing these be complicated. In particular, when semantic are reconstructed from point cloud data, uneven density noise make it difficult to accurately determine façade structure. When investigating layouts, Gestalt principles applied cluster visually si...

Identifying the association between long noncoding RNA (lncRNA) and micro-RNA (miRNA) is of great significance for treatment diseases by interfering with combination miRNA messenger (mRNA). Although many efforts resources have been invested to identify lncRNA-miRNA associations (LMAs), clinical trials are still expensive laborious. Nevertheless, experiments also need consult a large number side...