Michael Anslow

Today, powerful suites of natural language processing tools can be used to construct rich, spaghetti-like networks capturing the knowledge and semantics of text. Somewhere among these hotchpotch instantiations of various linguistic theories is a wealth of elaborate interconnected structures that capture something fundamental about natural language. Everything is connected, but which connections are important and for what? In my research, I explore how to automatically extract what is useful from such representations towards solving structure generation problems while attempting to find solutions that are agnostic to particular linguistic theories or problem domains. I am particularly interested in the problem of generating globally semantically coherent text, as this seems to be what is currently out of reach from the current state of the art and where I feel rich representations are crucial.

Natural language processing / Structure generation / Rich representations




During my bachelor's degree in computer science I gained an optimism for building, creating and understanding technical problems. Following this, I completed a master's degree in cognitive science at the University of Edinburgh where I gained a profound appreciation for the role that language has to play in intelligence - both artificial and natural. This inspired me to begin a PhD on the topic of semantic alignment between intelligent agents with heterogeneous experiences. Somewhere along the line, I became involved in the Marie Curie project on the Evolution of Shared SEmaNtics in Computational Environments (ESSENCE). I was closely affiliated with this project and eventually ended up joining the project in a position at Vrije Universiteit Brussels. During my time in Brussels, I had the opportunity to learn more about the evolution of language. I also had the fortune to become involved in the Horizon 2020 project on Opinion Dynamics and Cultural Conflict in the European Union (ODYCCEUS ) which peaked my wider interest in understanding people and society as a whole.

Go to top