
Nicola De Cao
language models
entity linking
named entity
attribution
planning
entity disambiguation
autoregressive generation
autoregressive entity linking
sparse interventions
differentiable masking
long-form question answering
8
presentations
10
number of views
SHORT BIO
I am an incoming Research Scientist at Google AI in London, UK. Previously, I did my Ph.D. at the Institute for Logic, Language and Computation (ILLC) of the University of Amsterdam and at the School of Informatics of the University of Edinburgh. I was a part of the EdinburghNLP and AmsterdamNLP groups.
I also interned at Huggingface and Facebook AI Research (FAIR) in London, UK and at Amazon Research in Berlin, Germany.
My work focuses on Machine Reading Comprehension, also known as Question Answering. In particular, I am working on neural models that retrieve information from a collection of documents and then answer complex questions. I also work on Entity Linking and Entity Disambiguation. More generally, I am interested in (semi-)supervised and unsupervised deep neural network applications in combination with reasoning and reinforcement methods to approach Natural Language Understanding.
Presentations

Learning to Plan and Generate Text with Citations
Constanza Fierro and 6 other authors

Sparse Interventions in Language Models with Differentiable Masking
Nicola De Cao

GenIE: Generative Information Extraction
Martin Josifoski and 4 other authors

Multilingual Autoregressive Entity Linking
Nicola De Cao and 9 other authors

Editing Factual Knowledge in Language Models
Nicola De Cao

Editing Factual Knowledge in Language Models
Nicola De Cao

Highly Parallel Autoregressive Entity Linking with Discriminative Correction
Nicola De Cao

Highly Parallel Autoregressive Entity Linking with Discriminative Correction
Nicola De Cao