Master Lab Course - Machine Learning for Natural Language Processing Applications (IN2106, IN4249)
Course 0000004166 in SS 2020
General Data
Course Type | practical training |
---|---|
Semester Weekly Hours | 6 SWS |
Organisational Unit | Informatics 2 - Chair of Formal Languages, Compiler Construction, Software Construction (Prof. Seidl) |
Lecturers |
Gerhard Johann Hagerer Maximilian Wich Monika Wintergerst Responsible/Coordination: Georg Groh |
Dates |
Mon, 09:00–11:00, MI 03.09.012 and 1 singular or moved dates |
Assignment to Modules
-
IN2106: Master-Praktikum / Advanced Practical Course
This module is included in the following catalogs:- Further Modules from Other Disciplines
Further Information
Courses are together with exams the building blocks for modules. Please keep in mind that information on the contents, learning outcomes and, especially examination conditions are given on the module level only – see section "Assignment to Modules" above.
additional remarks | People are increasingly using text-based forms of communication, including social media, to exchange impressions of their everyday life or to get ideas for their individual lifestyle. As a result, a large amount of text data is available online, containing a wealth of information on various topics. This results in new use cases, which have implications for research on machine learning in the field of natural language processing. To this end, recent advances in this technical field appear promising, as they mimic human understanding of text by capturing and extracting universal semantic knowledge from large text resources. Therefore, we offer appropriate research literature, based on which students use state-of-the-art methods. These potentially involve neural networks and include semantic embedding, attention mechanisms, transfer learning, clustering algorithms, and unsupervised and supervised approaches. The lab is divided into three different application areas in terms of content and organization: - Text-based dialogue systems and recipe ingredient substitution for virtual dietary advisors - Text mining for the quantitative support of opinion research on text data from social media - Explainable artificial intelligence and hate speech detection in text data from social media |
---|---|
Links |
E-Learning course (e. g. Moodle) TUMonline entry |