M.Sc. Niklas Rach

Research

PhD Thesis

Embedded Aigaion Query

Argumentative Dialogue Systems

Resolving different viewpoints of virtual agents can be addressed as a dialogical task in which arguments are exchanged. Thereby it is possible for each side to persuade the opponents by establishing a convincing argumentation structure. An Argumentative Dialogue System is a system that allows an agent to carry out argumentative task such as persuasion or negotiation against a human. Despite the strong theoretical grounding, implementations of these kind of systems are rather scarce since they have to overcome different obstacles.

In my thesis I address two important issues of such a system, namely the Natural Language Understanding (NLU) of arguments and the development of a flexible agent strategy.

Research Interests

  • Non-cooperative Dialogue Systems
  • Computational Argumentation
  • Machine Learning

Publications

2015
N. Rach, M.Müller, T. Calarco, and S. Montangero
Dressing the chopped-random-basis optimization: A bandwidth-limited access to the trap-free landscape
Physical Review A - Atomic, Molecular, and Optical Physics

2016
N. Rach, S. Montangero, and M. Paternostro
Optimal control of many-body non-equilibrium quantum thermodynamics
arXiv:1605.07476

Embedded Aigaion Query 2017

N. Rach, W. Minker and S. Ultes
Interaction Quality Estimation Using Long Short-Term Memories
Proceedings of the 18th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), Association for Computational Linguistics, Saarbrücken, Germany, pp. 164--169, August 2017
Bibtex

N. Rach, W. Minker and S. Ultes
Towards an Argumentative Dialogue System
Proceedings of 17th Workshop on Computational Models of Natural Argument (CMNA'17), London, UK, June 2017
Link to Document
Bibtex

Teaching

Teaching Assistance

Projects and Seminars

MSc/BSc Topics

Open Topics

Embedded Aigaion Query

Ich betreue gerne Bachelor und Master Arbeiten aus dem Bereich meines Promotionsthemas. Schreibe mir einfach eine E-Mail, wenn du Interesse hast.

I am pleased to supervise Bachelor and Master Theses within my PhD Topic. Just write an email if you are interested.

In Progress / Completed

Embedded Aigaion Query 2017

Bachelor Thesis
A debating ontology for Argumentative Dialogue Systems
2017
Link to Document

Research Assistant