Besides being a collection of characters, text is up util now still considered to be one of the most commonly used medium of communication. The complex nature of textual data as well as their sheer amount though make building data mining models challenging. As part of the Master's Program in Media Informatics at the Bonn-Aachen International Center for Information Technology (B-IT), this course will cover the state-of-the-art and established methods for mining textual datasets . The course will start with a lecture series on the preliminaries of data mining and machine learning, continue with a deep dive on advanced text mining methods involving Latent Semantic Indexing, Word Embeddings, traditional and resource efficient Recurrent Neural Networks for sequential representations from textual data, Attention Mechanism as well as Transformer architectures and end with lectures on applications from real wold involving natural language inference and information extraction in financial documents, recommender systems in the legal and audit domain and generative models for digital forensics.
Prerequisites: Basic knowledge of AI, data science, machine learning, and pattern recognition; programming skills; good working knowledge in statistics, linear algebra, and optimization. Having taken the related B-IT courses Mining Media Data I and Mining Media Data II is not a must. The course has 4-ETCS credits (with 2+2 SWS) and is taught by Dr. Rafet Sifa. The teaching assistant of the course will be Tobias Deußer. One week prior to each lecture a list of recommended readings (from text books, reports and research papers) related to the course work will be announced. For questions as well as the registration (see the news below) please write to bit.am4tm@gmail.com.
[23.11.22] Slides of the third exercise session (Backpropagation) are online. The time slots for lecture and exercise session are swapped tomorrow, thus the lecture is going to start at 12:15 and the exercise session is going to start at 14:00.
[17.11.22] First Assignment is online. Remember that the deadline is the December 1st, 2022, at 12:15 (right before the exercise session).
[16.11.22] Slides of the second lecture (Preliminaries: Machine Learning and Optimization 1) are online
[14.11.22] Slides of the second exercise session (ML Basics) are online
[02.11.22] Slides of the first exercise session (NLP Basics) are online
[27.10.22] Slides of the first lecture are online
[22.09.22] In this semester the course on Advanced Methods for Text Mining will be taught for the University of Bonn as well as the RWTH students at the Bonn-Aachen International Center for Information Technology (B-IT) in Friedrich-Hirzebruch-Allee 6, 53115 Bonn, Germany. Due to introductory events at the B-IT for the newcomers, the first lecture will take place on the 27.10.22 at 14:00 in the lecture hall (ger. Hörsaal) 0.109. If you are interested in taking this course, there will be two registration periods. First period for content- and mailing-list registration ends on 30.11.22 at 9:30 (CEST). In order to get access to the course material (as well as information about the lecture hall, exercise sheets and etc.) and get added to the mailing list, the students are asked to send their names, email addresses, matriculation numbers and their study programs (e.g. M.Sc. in Media Informatics) to bit.am4tm@gmail.com (only mails from university email addresses will be considered). The mail should be titled as Registration WS2223 and the content should have the student's information in one line formatted in a comma-separated fashion: MATRICULATION_NUMBER, UNIVERSITY_EMAIL, NAME, SURNAME, PROGRAM (e.g. 12345,jamie.mustermann@my-university.de,Jamie,Mustermann, M.Sc. in Media Informatics). The second and the final registration period will end on 10.12.22 at 9:30 (CEST). The students will receive an email informing them about the course after the end of each registration period.