Encoding Linguistic Structures with Graph Conv. Networks: Diego Marcheggiani

title: Encoding Linguistic Structures with Graph Convolutional Networks

abstract:
Graph Convolutional Networks (GCNs) is an effective tool for modeling graph-structured data.
We investigate their applicability in the context of natural language processing (semantic role labeling and machine translation)
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 state-of-the-art results on semantic role labeling of English and Chinese and a substantial boost in machine translation performance.

bio:
Diego Marcheggiani is a postdoctoral researcher at the University of Amsterdam and "permanent" visiting researcher at the University of Edinburgh.
He graduated with a Ph.D. in Computer Science from the University of Venice and during this period he worked at the ISTI-CNR in Pisa (Italy) as a researcher.
His research focus is on supervised and unsupervised (deep) learning approaches for natural language understanding.
Diego is currently working on encoding, and inducing linguistic structures into/with neural networks.

note:
Babylon will be our host this time -- be aware that entering their office is under NDA.