Reading and Reasoning with Vector Representations

27^th September 2017, 13:00 Ashton Lecture Theater
Dr. Sebastian Riedel
University College London
Dept. of Computer Science (1ES)
Gower Street
London WC1E 6BT
United Kingdom

Abstract

In recent years, vector representations of knowledge have become popular in NLP and beyond. They have at least two core benefits: reasoning with (low-dimensional) vectors tends to lead to better generalisation, and usually scales very well. But they raise their own set of questions: What type of inferences do they support? How can they capture asymmetry? How can explicit background knowledge be injected into vector-based architectures? How can we provide “proofs” that justify predictions? In this talk, I sketch some initial answers to some of these questions based on our recent work. In particular, I will illustrate how a vector space can simulate the workings of logic.