11 August 2023
Treebanking: Methodology, Tools and Applications
This introductory course will present a general introduction to dependency-based syntactic treebanks and to two existing frameworks: Universal Dependencies (UD) and its variant Surface Syntactic Universal Dependencies (SUD). After the general introduction of the topic, we will describe a set of tools that are available to help the development of new treebanks (Grew-match and Arborator-grew), with a focus on under-resourced languages. We present some experiments applying these tools to the construction of new treebanks of Spoken French, Zaar, and Beja. Finally, we will illustrate a few applications which are currently developed in the Autogramm project. One application is the automatic extraction of grammatical observations from treebanks to help linguists in the study of the grammar of new languages (with an example of Wolof). A second application, the use of these annotated treebanks in quantitative typology will be presented.
Bruno Guillaume and Kim Gerdes
EUR 490: Early student registration
EUR 690: Early non-academic registration
There are several scholarship options which you can read about on our website.