ADRIEN GUILLE

Associate Professor of Computer Science @ Université Lumière Lyon 2

Graph-Based NLP

In this series of works we revisit classical natural language processing tasks by casting them as tasks defined on graphs, allowing the use of graph neural networks (GNN) to address them.

Contributions

In one research direction, we’ve proposed a graph-based approach to document classification, using a hierarchical GNN operating in the hyperbolic space ; we’ve also proposed a GNN-RNN architecture for extractive document summarization (presented at ECIR 2024). In another research direction, we have highlighted the capacity of pre-trained language models to linearly encode the structure of AMR (abstract meaning representation) graphs in the attention mechanism (presented at *SEM 2024).

Selected Publications

Code