Home > Research > Activities > A whistle stop tour of Natural Language Process...
View graph of relations

A whistle stop tour of Natural Language Processing and Corpus Linguistics methods and applications

Activity: Talk or presentation typesInvited talk


In these sessions consisting of a one hour lecture followed by a 1.5 hour hands-on lab, I will provide a broad overview of Natural Language Processing (NLP) and Corpus Linguistics (CL) methods and tools and illustrate applications and extensions of their methods with some small project case studies. While CL originally tended to focus on language description and analysis, its methods along with those in NLP have been more widely applied to social science disciplines and beyond, including challenges in the real-world such as dementia detection, metaphor in end-of-life care, online child protection, biomedical and financial text mining. NLP and CL researchers analyse language at a number of levels, from lexical, grammatical, syntactic, semantic, pragmatic and discourse, and much work focusses on annotation to add interpretative linguistic information into corpora to reduce ambiguity for further levels of analysis. In particular, I will highlight NLP methods for semantic annotation, and show why multiword expressions are important. This will lead into the hands-on lab session where participants will use version 4 of the Wmatrix corpus analysis and comparison tool and explore how Wmatrix combines NLP and CL methods for political discourse analysis.

Event (Course)

TitleTallinn University PhD Winter School on Human Computer Interaction and Educational Technology
LocationNelijärve Holiday house
Degree of recognitionNational event