Cross-Temporal NLP
Module Description
| Course | Module Abbreviation | Credit Points |
|---|---|---|
| BA-2010 | AS-CL, AS-FL | 8 LP |
| BA-2010[100%|75%] | CS-CL | 6 LP |
| BA-2010[50%] | BS-CL | 6 LP |
| BA-2010[25%] | BS-AC | 4 LP |
| Master | SS-CL-TAC | 8 LP |
| Lecturer | Wei Zhao |
| Module Type | Hauptseminar / Proseminar |
| Language | Englisch |
| First Session | 14.10.2025 |
| Time and Place | Tuesday, 15:15 - 16:45, Online |
| Commitment Period | tbd. |
Participants
All advanced CL Bachelor students and all CL master students. Students from MSc Data and Computer Science or MSc Scientific Computing with Field of Application Computational Linguistics are welcome after getting permission from the lecturer.MSc Scientific Computing students can only take the course as HS for 8 LP. If the seminar should be oversubscribed, CL students will have priority.
Prerequisites for Participation
- Introduction to Computational Linguistics or similar introductory courses
- Introduction to Neural Networks and Sequence-To-Sequence Learning (or equal)
- Completion of Programming I
Assessment
- Active Participation
- Presentation
- Term Paper Writing
Contents
Temporality is a fundamental aspect of NLP technologies, which is extremely underrepresented in the NLP community compared to other widely recognized aspects such as multilinguality, cross-culturality, and multimodality. With the advent of LLMs, there have been many time-sensitive applications such as temporal reasoning, forecasting, and planning. Moreover, a growing number of interdisciplinary works rely on NLP technologies for cross-temporal studies in fields such as social science, psychology, cognitive science, environmental science, and clinical studies. Therefore, temporality has become a crucial aspect in NLP.
However, LLMs are hindered in their understanding of time due to many different reasons, including temporal biases and knowledge conflicts in pretraining and RAG data but also a fundamental limitation in LLM tokenization that fragments a date into several meaningless subtokens. Such inadequate understanding of time would potentially lead to inaccurate reasoning, forecasting and planning, and incorrect scientific discoveries if they are time-sensitive.
In this course, we will look into several issues in cross-temporal NLP and works that blend temporality into multilinguality, cross-culturality, and multimodality, as well as interdisciplinary applications beyond NLP.
Course materials are available here.
