Deep Language Processing Using Construction Grammars

Practical course run by Remi van Trijp and Paul Van Eecke

Construction Grammar is an innovative approach to language that focuses strongly on semantics, cognitive processes and learning. As such, it has the potential to lead to more powerful language technologies and more comprehensive accounts of language processing than psychology and computational linguistics are able to offer today. This course will teach its participants how the key concepts of construction grammar can be implemented in computational models for deep language processing that are capable of both comprehension and formulation. Moreover, students will also learn how to implement learning operators for more robust processing, and how to evaluate their grammars. Each session will take the form of a hands-on atelier using Fluid Construction Grammar (FCG), an advanced computational platform for developing constructional processing and learning models.


Summary of the Program

Date Morning (1.5h) Afternoon (1.5h)
15/03 Introduction to Fluid Construction Grammar + Writing Lexical Constructions Writing Grammatical Constructions for Argument Structure
16/03 Meta-layer Problem Solving and Learning of Constructions using Anti- and Pro-unification Evaluating Construction Grammars + Wrap-up

Detailed Program


Background Materials





Practical Details

This practical course is part of the Interdisciplinary College (IK) Spring School, which will take place at Möhnesee-Günne from 10-17 March 2017. The practical course on deep language processing using construction grammars will be taught on 15-16 March, in 4 sessions of 1.5 hours each.

Registration: Register through the main website of the Spring School.

More information: Remi van Trijp (


About the Course Instructors

Remi van Trijp Dr Remi van Trijp is the head of the language research unit at Sony Computer Science Laboratory Paris and one of the chief architects of Fluid Construction Grammar. He has pioneered the first constructional processing model for argument structure that works for both language comprehension and formulation, and has developed state-of-the-art agent-based language models for the emergence of grammar. In his latest work, he has focused on how robust models of constructional language processing can be applied for broad-coverage grammars.

Paul Van Eecke Paul Van Eecke is a member of the language research unit at Sony Computer Science Laboratory Paris. He has been involved in the development of Fluid Construction Grammar since 2014. His main research topics include (1) algorithms that make constructional language processing more robust and flexible and (2) algorithms that learn more abstract constructions from concrete observations.