More about HKUST
Quantum Information Flow Made Classical: New Mathematics for Natural Language Compositionality
====================================================================== Joint Seminar ====================================================================== The Hong Kong University of Science & Technology Human Language Technology Center Department of Computer Science and Engineering Department of Electronic and Computer Engineering --------------------------------------------------------------------- Speaker: Edward GREFENSTETTE Department of Computer Science Oxford University Title: "Quantum Information Flow Made Classical: New Mathematics for Natural Language Compositionality" Date: Monday, 2 September 2013 Time: 4:00pm - 5:00pm Venue: Lecture Theater F (near lifts 25 & 26), HKUST Abstract: Over the past few years, work bringing together the research interests of members of Oxford's Computational Linguistics Group and Quantum Group have yielded a generalisation of Montague Grammar's interaction between syntax and semantics to other syntactic formalisms and algebraic semantic representations. In particular, recent work has explored how syntactically conditioned models of compositional distributional semantics could be derived, and learned from data. In this talk, I will give a brief overview of this line of research, before offering some (very open ended) thoughts on the direction future work might take. No knowledge of particularly fancy mathematics (e.g. category theory) is expected, as all the technical bits will be explained through the medium of (hopefully) pretty pictures. ******************* Biography: Ed GREFENSTETTE is a Franco-American computer scientist. He recently finished a doctorate at the University of Oxford's Department of Computer Science under the supervision of Bob Coecke, Stephen Pulman and Mehrnoosh Sadrzadeh. He now works as a researcher in the same department, and teaches computer science and philosophy at Hertford College, where he is a lecturer. He is also a Fulford Junior Research Fellow at Somerville College. His main research interests are tensor-based models of semantics, applied category theory, and mathematical linguistics.