Besides making our thoughts more vivid and filling our communication with richer imagery, metaphor plays a fundamental structural role in our cognition, helping us to organise and project knowledge. For example, when we say “a well-oiled political machine”, we view the concept of political system in terms of a mechanism and transfer inferences from the domain of mechanisms onto our reasoning about political processes. Highly frequent in text, metaphorical language represents a significant challenge for natural language processing (NLP) systems. In this talk, I will first present a neural network architecture designed to capture the patterns of metaphorical use and its application to metaphor identification in text. I will then discuss how general-purpose lexical and compositional semantic models can be used to better understand metaphor processing in the human brain.
Ekaterina Shutova is an Assistant Professor at the Institute for Logic, Language and Computation at the University of Amsterdam. Her research is in the area of natural language processing with a specific focus on computational semantics, figurative language processing, multilingual NLP and cognitively-driven semantics. Previously, she worked at the University of Cambridge Computer Laboratory and the International Computer Science Institute and the Institute for Cognitive and Brain Sciences at the University of California, Berkeley. She received her PhD in Computer Science from the University of Cambridge in 2011.