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:
- | -
Digital Teaching:
Kick-off in Zoom:
19th Oct, 15:20-17:00
https://tu-darmstadt.zoom.us/j/84340601355?pwd=eTlhRUlCeVNYcUdnTHhOVGNZRnZTQT09
Course Contents:
Text Analytics: NLP for Document Processing
Natural language processing (NLP) has made considerable progress in the last decade, especially since the advancements of deep neural networks. Several of these technologies have been developed in academic research labs and were applied in real-world applications, powering several tasks like search, recommendation, autosuggestion, etc. Another promising subfield of NLP is document processing (e.g. scholarly articles, Wikipedia articles...). In this seminar, we will explore literature in this domain and look into the following questions:
- What are the drawbacks of current NLP technologies when applied to long documents?
- What are the document-level problems that can be solved with these approaches?
- How can we read academic literature critically and provide useful feedback on unpublished work?
Literature:
Will be announced during the seminar.
Preconditions:
Each student is expected to attend the initial online sessions where we will provide an overview of the topic. We will also discuss the peer review process. The students will be assigned papers based on their choice and they are expected to read the article critically and make a 2-page report covering different aspects of the paper. They will also be assigned 3 reports by fellow students and will be asked to write a 1 page summary of these reports. We will try to do a simulation of the actual peer review process prevalent in academia. We will also unveil a tool being developed by our department, which will make this process fun and interactive. Apart from report writing students are also expected to give a final presentation based on the paper assigned to them. Complete details will be announced during initial classes.
Further Grading Information:
Participants of this course will be graded based on:
- The presentation for their assigned topic
- The quality of the reports for their paper, and the quality of the reports they are expected to provide for other participants
More details of the quality criteria are given during the initial sessions.
|