** NEW ** You may now book your place through Proficio!
The ongoing transition from paper libraries to digital libraries, and the growth of social media are making automatic methods for classifying or extracting information from large amounts of textual data a necessity both to manage data, and to take advantage of the opportunities offered by such digitalization. This tutorial will cover the essential ideas in modern text analytics and their practical use.
The program will be as follows:
- Basic methods in text processing (preprocessing, statistical language modelling, parsing, vector-based models in IR)
- Text categorization (including sentiment analysis) and information extraction
- Using NLP pipelines
- Text classification