Exploring the Constructicon: Linguistic Analysis of a Computational CxG
This work provides a linguistic evaluation method for computational construction grammars, which is incremental as it builds on prior unsupervised approaches.
The paper tackled the evaluation of computational construction grammars by analyzing a learned constructicon from a linguistic perspective, finding that it can be categorized into nine major construction types, with Verbal and Nominal being most common, and demonstrating that token and type frequencies model variation across registers and dialects.
Recent work has formulated the task for computational construction grammar as producing a constructicon given a corpus of usage. Previous work has evaluated these unsupervised grammars using both internal metrics (for example, Minimum Description Length) and external metrics (for example, performance on a dialectology task). This paper instead takes a linguistic approach to evaluation, first learning a constructicon and then analyzing its contents from a linguistic perspective. This analysis shows that a learned constructicon can be divided into nine major types of constructions, of which Verbal and Nominal are the most common. The paper also shows that both the token and type frequency of constructions can be used to model variation across registers and dialects.