Speaker: Mark Steedman (University of Edinburgh)
The central role of syntax is to support semantics. The central problem of grammar is discontinuity, where elements that belong together in semantics as predicate and argument are separated in the sentence. The engine driving progress in the last fifty years of linguistics and natural language processing (NLP) can be seen as a search for a combinatory calculus, in which discontinuity is analysable in terms of operators over adjacent pairs of categories that are strictly contiguous in the sentence.
The talk is in three sections. In the first, I review this progress, the reasons why linguistic, psychological, and computational approaches to grammar have diverged, and how they are put back together in Combinatory Categorial Grammar (CCG), a formalism that has become widely used in NLP applications in which semantic interpretation plays a role, including semantic parsing, question-answering, and machine translation. In a second section, I briefly examine the question of why natural grammars should take the form of a combinatory calculus, rather than the more familiar linguistic formalisms. The last section turns to the question of whether any kind of grammar-based formalism still has a role to play in computational linguistics in the Age of Deep Learning and Recursive Neural Networks.
This talk is a version of an address given in response to the Lifetime Achievement Award of the Association for Computational Linguistics (ACL) in Melbourne in July 2018.
Mark Steedman is Professor of Cognitive Science in the School of Informatics at the University of Edinburgh, to which he moved in 1998 from the University of Pennsylvania, where he taught for many years as Professor in the Department of Computer and Information Science. He is a Fellow of the British Academy, the Royal Society of Edinburgh, the American Association for Artificial Intelligence (AAAI), the Association for Computational Linguistics (ACL), and the Cognitive Science Society (CSS), and a Member of the European Academy. In 2018, he was the recipient of the ACL Lifetime Achievement Award.
His research covers a wide range of problems in computational linguistics, natural language processing, artificial intelligence, and cognitive science, including syntactic and semantic theory, and parsing and interpretation of natural language text and discourse, including spoken intonation, by humans and by machine. Much of his current research uses Combinatory Categorial Grammar (CCG) as a formalism to address problems in wide-coverage parsing for robust semantic interpretation and natural language inference, and the problem of inducing and generalizing semantic parsers, both from data and in child language acquisition. Some of his research concerns the analysis of music using related grammars and statistical parsing models.