Dr.-Ing. Thomas Kleinbauer

Researcher

Saarland University
Saarland Informatics Campus
Bldg C 7 1, Room 0.07
66123 Saarbrücken

thomas.kleinbauer@lsv.uni-saarland.de
+49 681 302 58 130

Research Interests

  • A.I. and Society
    • Privacy in Voice Assistants
    • Hate-speech Detection
    • Appying A.I. to improve Democratic Discourse
  • Computational Linguistics
    • Spoken Dialog Systems
    • Discourse Management and Spoken Language Understanding
    • Statistical Natural Language Processing
  • Language and Thought
    • Frame Semantics

Past Gigs

2011 – 2013Research Fellow, Faculty of Information Technology, Prof. Dr. Ingrid Zukerman, Monash University, Melbourne, Australia
2004 – 2011Ph.D. at the Department for Artificial Intelligence, Prof. Dr. Dr. h.c. mult. Wolfgang Wahlster, Saarland University. Thesis title: „Automated Generation of Meeting Summaries“
2007 – 2008Visiting Scholar at the International Computer Science Institute (ICSI), FrameNet group, Prof. Charles J. Fillmore, Ph.D., Berkeley, California, USA
2008 – 2009
2004 – 2007		Researcher at the German Research Center for Artificial Intelligence (DFKI), Saarbrücken

Projects

M-PHASIS – Migration and Patterns of Hate Speech in Social Media – A Cross-cultural Perspective | 2019-2022 | ANR/DFG

Within Western societies, the issue of migration is often accompanied by high levels of public anxiety and translates to a significant increase of the use of hate speech towards immigrants and minorities. We study the patterns of hate speech related to migrants in user-generated content to provide a better understanding of its prevalence and emergence. – [More…]

COMPRISE – Cost-effective, Multilingual, Privacy-driven Voice-enabled Services | 2019-2022 | Horizon 2020

The project addresses the need for a fully private-by-design methodology and tools that will reduce the cost and increase the inclusiveness of voice interaction technology. To this end, our research advances on privacy-driven data transformations, personalised learning, automatic labelling, and integrated translation. – [More…]

METALOGUE – Multiperspective Multimodal Dialogue: dialogue system with metacognitive abilities | 2013-2016 | FP7-ICT – [More…]

D-BOX – A generic dialog box for multilingual conversational applications | 2012-2016 | Eurostars Eureka – [More…]

DORIS – A Spoken Language Interpretation Component for a Robot Dialogue System

AMIDA – Augmented Multiparty Interaction with Distant Access | 2006-2009 | EU IP | [More…]

AMI – Augmented Multiparty Interaction | 2004-2006 | EU IP | [More…]

Selected Publications

  1. David Ifeoluwa Adelani, Ali Davody, Thomas Kleinbauer, and Dietrich Klakow: Privacy Guarantees for De-identifying Text Transformations. In Proceedings of the 21st Annual Conference of the International Speech Communication Association (INTERSPEECH), October 26-29, 2020.
  2. Mossad Helali, Thomas Kleinbauer, and Dietrich Klakow: Assessing Unintended Memorization in Neural Discriminative Sequence Models. In Proceedings of the 23rd International Conference on Text, Speech and Dialogue (TSD 2020), September 8 – 11, 2020
  3. Michael Wiegand, Josef Ruppenhofer, Thomas Kleinbauer: Detection of Abusive Language: the Problem of Biased Datasets. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 602–608, Association for Computational Linguistics, Minneapolis, Minnesota, June 2019
  4. Thomas Kleinbauer and Thomas Trost: Comparing Distributional and Frame Semantic Properties of Words. In Proceedings of KONVENS 2018, Austria, September 2018 
  5. Martin Gropp, Anna Schmidt, Thomas Kleinbauer, Dietrich Klakow: Platon: Dialog Management and Rapid Prototyping for Multilingual Multi-User Dialog Systems. In Proceedings of the 19th International Conference on Text, Speech and Dialogue (TSD 2016), Brno, Czech Republic, September 12-16, 2016.
  6. Ingrid Zukerman, Su Nam Kim, Thomas Kleinbauer, and Masud Moshtaghi: Employing distance-based semantics to interpret spoken referring expressions. Computational Speech and Language 34(1): pp. 154-185, Elsevier, 2015
  7. Su Nam Kim, Ingrid Zukerman, Thomas Kleinbauer, and Masud Moshtaghi: A Comparative Study of Weighting Schemes for the Interpretation of Spoken Referring Expressions. In Proceedings of the Australasian Language Technology Association Workshop 2014, pp. 50-58, ALTA, Melbourne, Australia, November 26-28, 2014
  8. Thomas Kleinbauer, Ingrid Zukerman, and Su Nam Kim: Evaluation of the Scusi? Spoken Language Interpretation System – A Case Study. In Proceedings of the Sixth International Joint Conference on Natural Language Processing, pp. 225-233, Asian Federation of Natural Language Processing, Nagoya, Japan, October 14-18, 2013
  9. Su Nam Kim, Ingrid Zukerman, Thomas Kleinbauer, Farshid Zavareh: A Noisy Channel Approach to Error Correction in Spoken Referring Expressions. In Proceedings of the Sixth International Joint Conference on Natural Language Processing, pp. 234-242, Asian Federation of Natural Language Processing, Nagoya, Japan, October 14-18, 2013
  10. Farshid Zavareh, Ingrid Zukerman, Su Nam Kim, and Thomas Kleinbauer: Error Detection in Automatic Speech Recognition. In Proceedings of the Australasian Language Technology Association Workshop 2013 (ALTA 2013), pp. 101-105, Brisbane, Australia, December 2013