news

Nomination for the Goethe-University Innovation Prize

The Bundestags-Mine has been nominated for the Innovation Prize of the Goethe-University!


A final pitch will take place on December 10th, 2024 at 6 PM in the Festsaal Casino at Campus Westend. All the finalists will compete for the final ranking and the corresponding prize money, which is sponsored by the Sparkasse Foundation. If you’d like to join, tickets are freely avaiable on eventbrite.

The project idea was initiated through a lecture held by Prof. Dr. Alexander Mehler and Giuseppe Abrami. After the course ended, it was continued privately by one of the students, Kevin Bönisch, while maintaining contact with the Text Technology Lab. In 2023, the project was published in the Frontiers in Artificial Intelligence and Applications series, again through the Text Technology Lab in conjuction with Sabine Wehnert from the Georg-Eckert-Institut.


The Bundestags-Mine leverages artificial intelligence to analyze various data formats from the German Bundestag, including plenary proceedings, polls, agenda items, and more. The processed data is curated within the platform and made available for download. All data is freely accessible and can be obtained directly from the Bundestags-Mine website. This approach enables personalized access to the vast amounts of data produced daily by the German Bundestag, making politics more accessible. Additionally, it utilizes state-of-the-art AI techniques for advanced analysis, including sentiment analysis, topic modeling, summarization, and more, provided by the tools that were developed within the Text Technology Lab.


The Text Technology Lab actively encourages students to go beyond expectations, supporting them in publishing their first scientific papers, bachelor’s or master’s theses, and, as demonstrated in this example, achieving distinguished awards. The lab also provides guidance and infrastructure for large-scale research projects when necessary.

So if you are interested in research projects, bachelor’s or master’s theses that align with our research, or have other inquiries, feel free to contact us.


Two new papers at SemDial 2024 — TrentoLogue

The Semantics and Pragmatics of Dialogue, September 11th – 12th, 2024

On gesture semantics:

Andy Lücking, Alexander Mehler and Alexander Henlein. 2024. The Linguistic Interpretation of Non-emblematic Gestures Must be agreed in Dialogue: Combining Perceptual Classifiers and Grounding/Clarification Mechanisms. Proceedings of the 28th Workshop on The Semantics and Pragmatics of Dialogue.
BibTeX
@inproceedings{Luecking:Mehler:Henlein:2024-classifier,
  title     = {The Linguistic Interpretation of Non-emblematic Gestures Must
               be agreed in Dialogue: Combining Perceptual Classifiers and Grounding/Clarification
               Mechanisms},
  author    = {Lücking, Andy and Mehler, Alexander and Henlein, Alexander},
  year      = {2024},
  booktitle = {Proceedings of the 28th Workshop on The Semantics and Pragmatics of Dialogue},
  series    = {SemDial'24 -- TrentoLogue},
  location  = {Università di Trento, Palazzo Piomarta, Rovereto},
  url       = {https://www.semdial.org/anthology/papers/Z/Z24/Z24-4031/},
  pdf       = {http://semdial.org/anthology/Z24-Lucking_semdial_0031.pdf}
}

On brain-based semantics:

Jonathan Ginzburg, Chris Eliasmith and Andy Lücking. 2024. Swann's name: Towards a Dialogical Brain Semantics. Proceedings of the 28th Workshop on The Semantics and Pragmatics of Dialogue.
BibTeX
@inproceedings{Ginzburg:Eliasmith:Luecking:2024-swann,
  title     = {Swann's name: {Towards} a Dialogical Brain Semantics},
  author    = {Ginzburg, Jonathan and Eliasmith, Chris and Lücking, Andy},
  year      = {2024},
  booktitle = {Proceedings of the 28th Workshop on The Semantics and Pragmatics of Dialogue},
  series    = {SemDial'24 -- TrentoLogue},
  location  = {Università di Trento, Palazzo Piomarta, Rovereto},
  url       = {https://www.semdial.org/anthology/papers/Z/Z24/Z24-3007/},
  pdf       = {http://semdial.org/anthology/Z24-Ginzburg_semdial_0007.pdf}
}

New Publication Accepted for the 2nd Workshop on Legal Information Retrieval meets AI (LIRAI24)

Our paper, “Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles,” has been accepted to the 2nd Workshop on Legal Information Retrieval Meets AI. In this work, we present an approach that leverages embedding spaces, bootstrap aggregation, and SVR ensembles to retrieve legal passages efficiently, demonstrating improved recall compared to baseline methods (0.849 > 0.803 | 0.829):

Kevin Bönisch and Alexander Mehler. 2024. Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval via Bagging and SVR Ensembles. Proceedings of the 2nd Legal Information Retrieval meets Artificial Intelligence Workshop LIRAI 2024.
BibTeX
@inproceedings{Boenisch:Mehler:2024,
  title     = {Finding Needles in Emb(a)dding Haystacks: Legal Document Retrieval
               via Bagging and SVR Ensembles},
  author    = {B\"{o}nisch, Kevin and Mehler, Alexander},
  year      = {2024},
  booktitle = {Proceedings of the 2nd Legal Information Retrieval meets Artificial
               Intelligence Workshop LIRAI 2024},
  location  = {Poznan, Poland},
  publisher = {CEUR-WS.org},
  address   = {Aachen, Germany},
  series    = {CEUR Workshop Proceedings},
  abstract  = {We introduce a retrieval approach leveraging Support Vector Regression
               (SVR) ensembles, bootstrap aggregation (bagging), and embedding
               spaces on the German Dataset for Legal Information Retrieval (GerDaLIR).
               By conceptualizing the retrieval task in terms of multiple binary
               needle-in-a-haystack subtasks, we show improved recall over the
               baselines (0.849 > 0.803 | 0.829) using our voting ensemble, suggesting
               promising initial results, without training or fine-tuning any
               deep learning models. Our approach holds potential for further
               enhancement, particularly through refining the encoding models
               and optimizing hyperparameters.},
  archiveprefix = {arXiv},
  eprint    = {2501.05018},
  url       = {https://arxiv.org/pdf/2501.05018},
  keywords  = {legal information retrieval, support vector regression, word embeddings, bagging ensemble}
}