Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...
Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous Graph Neural Networks (GNN) require a large number of labeled ...
JavaBIP allows the coordination of software components by clearly separating the functional and coordination aspects of the system behavior. JavaBIP implements the principles of the BIP component framework rooted in rigorous operational semantics. Recent w ...
Developers turn ideas, designs and patterns into source code, then compile the source code into executables. Decompiling turns executables back into source code, and deprogramming turns code back into designs and patterns. In this paper we introduce DeP, a ...