|
Instructors: Prof. Dr. phil. Iryna Gurevych
Event type:
Seminar
Org-unit: Dept. 20 - Computer Science
Displayed in timetable as:
Text Analytics
Subject:
Crediting for:
Hours per week:
2
Language of instruction:
German
Min. | Max. participants:
- | -
Course Contents:
Seminar Topic: Text Analytics: Machine Learning for Text
Text analytics is about the extraction of useful knowledge from texts. The ubiquity of texts in Web, social networks, emails, and digital libraries makes the need for the text processing approaches imperative. In recent years, leveraging machine learning methods for analyzing texts has received a lot of attention. But, what makes learning from texts specific? How should texts be represented for machine learning models? How can machine learning models discover hidden semantic information in texts?
This seminar is going to answer these questions by coherently introducing various text-centric machine learning approaches from basic algorithms (e.g., rule-based) to advanced models (e.g., deep neural networks). The seminar covers a wide spectrum of fascinating topics such as text clustering, text classification, heterogeneous data, and feature selection. We discuss exciting applications of these approaches. Examples include information extraction, text summarization, sentiment analysis, and text segmentation. By the end of this seminar, students gain the knowledge of how to apply machine learning approaches to solve text-centric problems.
Literature:
Most content of this seminar is provided from the following book: “Machine Learning for Text” by Charu C. Aggarwal, published 2018. Other literature will be announced during the seminar.
Preconditions:
Each student is expected to:
- attend the seminar sessions and actively contribute to discussions during the seminar,
- develop a presentation on a topic relevant to the seminar,
- present the topic and answer the questions from the audience, and
- write a paper on the chosen topic.
|
