Construction Grammar was founded on the promise of maximal empirical coverage without compromising on formal precision. Its main claim is that all linguistic knowledge can be represented as constructions, similar to the notion of constructions from traditional grammars. As such, Construction Grammar may finally reconcile the needs of descriptive and theoretical linguistics by establishing a common ground between them. Unfortunately, while the construction grammar community has developed a sophisticated understanding of what a construction is supposed to be, many critics still believe that a construction is simply a new jacket for traditional linguistic analyses and therefore inherits all of the problems of those analyses. The goal of this article is to refute such criticisms by showing how constructions can be formalized as open-ended and multidimensional linguistic representations that make no prior assumptions about the structure of a language. While this article’s proposal can be simply written down in a pen-and-paper style, it verifies the validity of its approach through a computational implementation of German field topology in Fluid Construction Grammar.
