University of Cambridge > > Language Technology Lab Seminars > Graph Convolutional Networks for Natural Language Processing and Relational Modeling

Graph Convolutional Networks for Natural Language Processing and Relational Modeling

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Dimitri Kartsaklis.

Graph Convolutional Networks (GCNs) is an effective tool for modeling graph structured data. We investigate their applicability in the context of natural language processing (machine translation and semantic role labelling) and modeling relational data (link prediction). For natural language processing, we introduce a version of GCNs suited to modeling syntactic and/or semantic dependency graphs and use them to construct linguistically-informed sentence encoders. We demonstrate that using them results in a substantial boost in machine translation performance and state-of-the-art results on semantic role labeling of English and Chinese. We also experiment with GCNs over latent graphs (i.e. use structure of a sentence as a latent variable). For link prediction, we propose Relational GCNs (RGCNs), GCNs developed specifically to deal with highly multi-relational data, characteristic of realistic knowledge bases. By explicitly modeling neighbourhoods of entities, RGC Ns accumulate evidence over multiple inference steps in relational graphs and yield competitive results on standard link prediction benchmarks.

Joint work with Diego Marcheggiani, Michael Schlichtkrull, Joost Bastings, Thomas Kipf, Wilker Aziz, Max Welling, Khalil Sima’an, Rianna van den Berg and Peter Bloem.

This talk is part of the Language Technology Lab Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity