The event will be held on January 28 2020, and co-located with the ConSOLE conference. Its goal is that of introducing students, and in general researchers in Linguistics, to computational methods useful for the study of language.
Divergences in methods often constitute an obstacle for collaboration and communication between different branches of Linguistics. For instance, a discipline like Computational Linguistics requires a specialized training, which makes it hard to approach for researchers that are external to the field. With these tutorials, we aim to provide the attendees with a general introduction to Computational Linguistics, such that they can, more comfortably, e.g., read papers, attend talks, collaborate on projects, involving this discipline. With this action, we hope to foster contamination across different approaches to the study of language.
The event will consist of two tutorials, comprising a mix of lecture and hands-on practice. They will cover basic notions of programming for corpus analysis, and an introduction to modelling frameworks leveraging large-scale data (Distributional Semantics and in general machine learning). The tutorials will cover the basic technical aspects of these methods, as well as their motivations and applications. No prior knowledge of programming or computer science will be assumed. Attendees are required to bring a laptop to the tutorials, or alternatively work in small groups with at least one laptop.
14:30 Looking at natural language through Python
Lecturer: Matthijs Westera
This tutorial could be your first exposure to the Python programming language and its Natural Language ToolKit (NLTK). There will be hands-on exercises and we’ll reflect on how you could use Python and NLTK for your research. No prior familiarity with programming required.
The materials for this tutorial are here.
Natural Language Toolkit: https://www.nltk.org/ (especially https://www.nltk.org/book/)
16:00 Coffee break
16:30 Tutorial on data-driven methods in Computational Linguistics
Lecturer: Gemma Boleda
In this tutorial, we will aim at giving attendants a basic understanding of techniques in Machine Learning and Distributional Semantics, and discuss the interface between these methods and theoretical linguistics. The tutorial will be based on a talk and hands-on practice, and will cover the following contents:
The materials for this tutorial are here.
Recommended readings:
Organizing committee
Laura Aina
Ionut-Teodor Sorodoc