Vicente Ivan Sanchez Carmona I'm a fifthyear PhD student in computer science at University College London. I am part of the Machine Reading group. I'm working on understanding both representation learning systems (blackbox systems) and vector representations. For example, matrix factorization systems, word embeddings, and natural language inference systems. More concretely, I worked on: a) Extracting knowledge from a matrix factorization model, so one could understand why this complex model made a particular prediction. This knowledge is in the form of an interpretable model such as logic rules, decision trees and Bayesian networks. These interpretable models allow us to explain how the matrix factorization arrived to a particular output. (AAAI spring symposium and Cognitive Computation workshop papers) b) Understanding to what extent pretrained word embeddings encode a hypernymy relation, i.e. given the word embeddings of two concepts, can we know if the isa relationship holds between these two concepts only by inspecting the vector representations? Well, it turns out that into some extent we can. (EACL short paper 2017) c) Understanding what factors affect the robustness of natural language inference systems. (To appear at NAACL 2018) My interests are Machine Learning, Natural Language Processing, Data Mining, and Cognitive Science. News Next Invited Talks:
