Personal Information

Steffen Eger
Postdoctoral Researcher 

+49 (6151) 16 - 25299

+49 (6151) 16 - 25295
S2|02 B117

TU Darmstadt - FB 20 
Hochschulstraße 10 
64289 Darmstadt


Biographical Information

I am a postdoctoral researcher at UKP-TUDA.

I hold a M.A. (Magister Artium) in Computational Linguistics, Economics, and English from Ruprecht-Karls-University Heidelberg. I also hold a Diplom in Mathematics from the same university. In May 2014, I successfully defended my PhD thesis, with the title "Essays on Social Learning and Social Dynamics", from Goethe-University Frankfurt am Main. From April 2014 until February 2016, I worked as a postdoc at the Text Technology Lab in the CS department of Goethe-University. Since March 2016, I work at UKP. My current work focuses on Deep Learning methods for application scenarios such as Argumentation Mining.

Research Interests

  • Neural Nets, Deep Learning
  • Networks and Graphs (Linguistic, Social, Economical)
  • Alignments
  • String-to-string translation (in particular, G2P)
  • Computational Semantics
  • Machine Learning
  • General mathematics


Additional Attributes


Multi-Task Learning for Argumentation Mining in Low-Resource Settings

Claudia Schulz, Steffen Eger, Johannes Daxenberger, Tobias Kahse, Iryna Gurevych
In: Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, p. to appear, June 2018
Association for Computational Linguistics

Concatenated p-mean Word Embeddings as Universal Cross-Lingual Sentence Representations

Andreas Rücklé, Steffen Eger, Maxime Peyrard, Iryna Gurevych
In: arXiv, March 2018

Selected Publications

  • Eger, Steffen. Opinion dynamics and wisdom under out-group discrimination. Mathematical Social Sciences (80), pp. 97-107, 2016.
  • Eger, Steffen. On the number of many-to-many alignments of multiple sequences. Journal of Automata, Languages and Combinatorics 20 (2015) 1, 53-65.
  • Tim vor der Brück, Steffen Eger and Alexander Mehler. Complex Decomposition of the Negative Distance Kernel. In Proceedings of the IEEE International Conference on Machine Learning and Applications (ICMLA), Miami, Florida, 2015.
  • Eger, Steffen. Do we need bigram alignment models? On the effect of alignment quality on transduction accuracy in G2P. In: EMNLP 2015.
  • Eger, Steffen. Multiple Many-To-Many Sequence Alignment for Combining String-Valued Variables: A G2P Experiment, ACL 2015.
  • Eger, Steffen. Improving G2P from Wiktionary and other (web) resources, Interspeech 2015.
  • Eger, Steffen. Some Elementary Congruences for the Number of Weighted Integer Compositions, Journal of Integer Sequences, 2015.
  • Eger, Steffen. Identities for partial Bell polynomials derived from identities for weighted integer compositions. Aequationes Mathematicae, 2015.
  • Eger, Steffen. A proof of the Mann-Shanks primality criterion conjecture for extended binomial coefficients. Integers: The Electronic Journal of Combinatorial Number Theory (14), 2014, #A60.
  • Eger, Steffen. Stirling's approximation for central extended binomial coefficients. The American Mathematical Monthly, Vol. 121, No. 4 (April) (pp. 344-349), 2014.
  • Eger, Steffen, and Sejane, Ineta, (2010): Computing semantic similarity from bilingual dictionaries. JADT 2010: 10th International Conference on Statistical Analysis of Textual Data, 9-11 June 2010, Rome, Italy; pp.1217-1225.
A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang