M.Sc. Carolin Schindler

PhD Thesis

Embedded Aigaion Query

Towards Natural Multimodal Interaction with Argumentative Dialogue Systems

Argumentation is an essential element of human communication and reasoning. Whenever information is incomplete or inconsistent, we start to argue. This can take place internally as well as externally with other people or conversational agents. Recent works increase the flexibility of argumentative dialogue systems with respect to the possible topics of the argumentation. Still, the naturalness of the interaction with the dialogue system shows room for improvement.

Possible research directions are

the set of moves allowed by the system and the user,
the modalities perceived, processed, and evaluated by the dialogue system,
the modalities output/generated by the dialogue system,
the combination of different types of argumentative dialogue,
the communication strategy applied by the system, and
the extension and refinement of the underlying argumentation structure / knowledge base of the system and its automatic generation.

Research Interests

Natural Multimodal Human-Machine Interaction
Natural Language Processing, esp. in the field of Computational Argumentation
Aritificial Intelligence, esp. Machine Learning including Deep Learning

Achieved Academic Degrees

Master of Science in Cognitive Systems at Ulm University
Bachelor of Science in Informationssystemtechnik at Ulm University

Through my inter-disciplinary course of studies, my background is in Computer Science and Psychology as well as in Electrical Engineering.

Contributor

priority programme Robust Argumentation Machines (RATIO)
- phase 1: How to Win Arguments - Empowering Virtual Agents to Improve their Persuasiveness (EVA)
- phase 2: BEA - Building Engaging Argumentation
Self-Supporting Multimodal Interaction (SEMULIN)

Embedded Aigaion Query 2024

C. Schindler
Overlapping Aspect-based Argument Cluster Analysis including Cluster Labelling for Opinion Formation with Argumentative Dialogue Systems
Master's thesis, 2024
DOI

2021

N. Rach, C. Schindler, I. Feustel, J. Daxenberger, W. Minker and S. Ultes
From Argument Search to Argumentative Dialogue: A Topic-independent Approach to Argument Acquisition for Dialogue Systems
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, ACL, Singapore, 2021
Link to Document
Bibtex

2020

C. Schindler
Argumentative Relation Classification for Argumentative Dialogue Systems
Bachelor's thesis, 2020
DOI

Thesis and Project Topics for Students

When you are interested in working on a thesis or project within my PhD topic and research interests, just write me an email (Deutsch, English). Based on your background, we can discuss open topics and your own proposals.