A multi-day practical workshop on automatic morpho-syntactic annotation is coming up

On April 15-19th at 12PM-2 PM a practical workshop organized by the Center for Digital Humanities and Information Society will be held. The lecturer of the workshop is Hanna-Mari Kupari, a PhD student from the University of Turku. The workshop will be held in English and is titled 'A practical workshop on automatic morpho-syntactic annotation of large language corpora using the Universal Dependencies framework'.

You can participate in the workshop without any prior knowledge, but please bring your own laptop!

Description of the workshop

This workshop includes a short general introduction to machine learning related to automatic morphosyntactic parsing. After attending this you will know how to use some of the most common types of tools for morpho-syntactic parsing. We will use the neural network based parser Trankit and the Stanza pipeline. You will also practice forming and answering your own relevant research questions with a morpho-syntactically parsed corpus in the Universal Dependencies framework.

Overview of the lecturer

Hanna-Mari Kupari is a doctoral researcher in digital linguistics at the University of Turku, Finland, specialised in medieval Latin. She did her MA in classical philology using quantitative methods. After that her work has focused on the use of modern digital humanities methods on historical data: making structured machine readable data and developing tools for automatic linguistic annotation. She has a particular interest in the study of variation in language use and morpho-syntactic parsing.