Past News
October 04, 2021 - KONVENS proceedings available
And just a couple of days later, our more recent paper Benchmarking down-scaled (not so large) pre-trained language models is now also available within the official conference proceedings of this year's KONVENS.
September 30, 2021 - SwissText proceedings available
Our paper Re-Evaluating GermEval17 Using German Pre-Trained Language Models is now available within the official conference proceedings.
July 22, 2021 - Paper accepted at KONVENS
Our paper "Benchmarking down-scaled (not so large) pre-trained language models" has been accepted for presentation at this year's KONVENS.
[Link to the pre-print on arXiv // Authors: M. Aßenmacher, P. Schulze & C. Heumann]
July 22, 2021 - New master thesis offering [Update: The topic is already taken]
We have a new offering for a master thesis: Topic modeling via Constrained Clustering
[Supervisors: C. Heumann, M. Aßenmacher, J. Goschenhofer]
July 8, 2021 - Paper published in PLOS ONE
Our paper "Multiple imputation with compatibility for high-dimensional data" has been published in the open access journal PLOS ONE.
[Link to the paper // Authors: F. M. Zahid, S. Faisal & C. Heumann]
June 16, 2021 - Best Presentation Award at SwissText 2021
For the presentation of our paper "Re-Evaluating GermEval17 Using German Pre-Trained Language Models" we were awarded the "Best Presentation Award" at SwissText 2021.
[Slides // Certificate // Authors: M. Aßenmacher, A. Corvonato & C. Heumann]
May 11, 2021 - Pre-Print available on arXiv
A pre-print of our paper "Benchmarking down-scaled (not so large) pre-trained language models" is now available on arXiv.
[Link to the pre-print // Authors: M. Aßenmacher, P. Schulze & C. Heumann]
April 23, 2021 - Paper accepted at SwissText 2021
Our paper "Re-Evaluating GermEval17 Using German Pre-Trained Language Models" was accepted at SwissText 2021.
[Link to the accepted submissions // Authors: M. Aßenmacher, A. Corvonato & C. Heumann]
April 07, 2021 - Pre-Print available on arXiv
A pre-print of our paper "Exploring Topic-Metadata Relationships with the STM: A Bayesian Approach" is now available on arXiv.
[Link to the pre-print // Authors: P. Schulze, S. Wiegrebe, P. W. Thurner, C. Heumann, M. Aßenmacher & S. Wankmüller]
February 25, 2021 - Pre-Print available on arXiv
A pre-print of our paper "Re-Evaluating GermEval17 Using German Pre-Trained Language Models" is now available on arXiv.
[Link to the pre-print // Authors: M. Aßenmacher, A. Corvonato & C. Heumann]
February 08, 2021 - Paper published in Applied Marketing Analytics
The outcome of a consulting project carried out in cooperation with Insaas and two very motivated students from LMU was published in the journal Applied Marketing Analytics. The title of the paper is "Creating a ‘customer centricity graph’ from unstructured customer feedback".
[Link to the paper // Authors: E. Lebmeier, N. Hou, K. Spann & M. Aßenmacher]
January 09, 2021 - Talk at KOINet workshop
We gave a talk entitled "Large Pre-trained Language Models – can social sciences also benefit from recent
developments in NLP?" at the KOINet workshop "New Tools for Old Problems".
[Link to the slides]
December 07, 2020 - Pre-Print available on arXiv
A pre-print of our paper "Pre-trained language models as knowledge bases for Automotive Complaint Analysis" is now available on arXiv.
[Link to the pre-print // Authors: V. D. Viellieber & M. Aßenmacher]
November 12, 2020 - Paper accepted at ICAART 2021
Our paper "A new Benchmark for NLP in Social Sciences: Evaluating the usefulness of pre-trained language models for classifying open-ended survey responses" was accepted at the 13th International Conference on Agents and Artificial Intelligence!
[Link to the paper // Authors: M. Meidinger & M. Aßenmacher]
October 1, 2020 - Paper accepted at COLING 2020
Our paper "Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News" was accepted at the 28th International Conference on Computational Linguistics!
[Link to the paper // Authors: M. Guderlei & M. Aßenmacher]
September 3, 2020 - Book from our seminar "Modern Approaches in Natural Language Processing"
We published a small booklet as the result of our NLP seminar in the summer term 2020. This is the great result of the collective effort from a handfull of extremely motivated Statistics & Data Science master students!
[Link to the book // Link to GitHub]
August 27, 2020 - Further Resources for Statistics I & II for Economists
We published an accompanying manuscript for Statistics I & II for Economists with further explanations, examples & R-references. A huge thanks to all collaborators for this collective effort!
[Link to the manuscript on GitHub // Authors: M. Aßenmacher, A.K. Köpple, C. Luther, P. Haro, M. Mandl]
July 27, 2020 - Research proposal for a master thesis
We are offering a master thesis together with the chair of Statistical Learning and Data Science.
[Link to the research proposal // Supervisors: D. Rügamer, P. Kopper, M. Aßenmacher]
June 18, 2020 - Publication of the paper "On the comparability of pre-trained language models"
Our work "On the comparability of pre-trained language models" has been published in the proceedings of SWISSTEXT & KONVENS 2020 which takes place from June 23 - 25, 2020.
[Link to our paper // Link to the full proceedings // Authors: M. Aßenmacher & C. Heumann]