47 citations · 115 across the 30 of their papers we have counts for
3 papers · 1 filter
How to detect novelty in textual data streams? A comparative study of existing methods
Clément Christophe, Julien Velcin, Jairo Cugliari +2
Since datasets with annotation for novelty at the document and/or word level are not easily available, we present a simulation framework that allows us to create different textual…
Link Prediction with Mutual Attention for Text-Attributed Networks
Robin Brochier, Adrien Guille, Julien Velcin
In this extended abstract, we present an algorithm that learns a similarity measure between documents from the network topology of a structured corpus. We leverage the Scaled Dot-P…
Global Vectors for Node Representations
Robin Brochier, Adrien Guille, Julien Velcin
Most network embedding algorithms consist in measuring co-occurrences of nodes via random walks then learning the embeddings using Skip-Gram with Negative Sampling. While it has pr…