Corpora

@InProceedings{Abrami:Bagci:Hammerla:Mehler:2022,
  author    = {Abrami, Giuseppe  and  Bagci, Mevlüt  and  Hammerla, Leon  and  Mehler, Alexander},
  title     = {German Parliamentary Corpus (GerParCor)},
  booktitle      = {Proceedings of the Language Resources and Evaluation Conference},
  month          = {June},
  year           = {2022},
  address        = {Marseille, France},
  publisher      = {European Language Resources Association},
  pages     = {1900--1906},
  abstract  = {Parliamentary debates represent a large and partly unexploited treasure trove of publicly accessible texts. In the German-speaking area, there is a certain deficit of uniformly accessible and annotated corpora covering all German-speaking parliaments at the national and federal level. To address this gap, we introduce the German Parliamentary Corpus (GerParCor). GerParCor is a genre-specific corpus of (predominantly historical) German-language parliamentary protocols from three centuries and four countries, including state and federal level data. In addition, GerParCor contains conversions of scanned protocols and, in particular, of protocols in Fraktur converted via an OCR process based on Tesseract. All protocols were preprocessed by means of the NLP pipeline of spaCy3 and automatically annotated with metadata regarding their session date. GerParCor is made available in the XMI format of the UIMA project. In this way, GerParCor can be used as a large corpus of historical texts in the field of political communication for various tasks in NLP.},
  poster   = {https://www.texttechnologylab.org/wp-content/uploads/2022/06/GerParCor_LREC_2022.pdf},
  pdf    = {http://www.lrec-conf.org/proceedings/lrec2022/pdf/2022.lrec-1.202.pdf}

}

@InProceedings{Ahmed:Mehler:2018,
author = {Sajawel Ahmed and Alexander Mehler},
title = {{Resource-Size matters: Improving Neural Named Entity Recognition with Optimized Large Corpora}},
abstract = {This study improves the performance of neural named entity recognition by a margin of up to 11% in terms of F-score on the example of a low-resource language like German, thereby outperforming existing baselines and establishing a new state-of-the-art on each single open-source dataset (CoNLL 2003, GermEval 2014 and Tübingen Treebank 2018). Rather than designing deeper and wider hybrid neural architectures, we gather all available resources and perform a detailed optimization and grammar-dependent morphological processing consisting of lemmatization and part-of-speech tagging prior to exposing the raw data to any training process. We test our approach in a threefold monolingual experimental setup of a) single, b) joint, and c) optimized training and shed light on the dependency of downstream-tasks on the size of corpora used to compute word embeddings.},
booktitle = {Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA)},
location = {Orlando, Florida, USA},
pdf = {https://arxiv.org/pdf/1807.10675.pdf},
year = 2018
}

@InProceedings{Luecking:Mehler:Walther:Mauri:Kurfuerst:2016,
  Author         = {L\"{u}cking, Andy and Mehler, Alexander and Walther,
                   D\'{e}sir\'{e}e and Mauri, Marcel and Kurf\"{u}rst,
                   Dennis},
  Title          = {Finding Recurrent Features of Image Schema Gestures:
                   the {FIGURE} corpus},
  BookTitle      = {Proceedings of the 10th International Conference on
                   Language Resources and Evaluation},
  Series         = {LREC 2016},
  location       = {Portoro\v{z} (Slovenia)},
  pdf            = {http://www.texttechnologylab.org/wp-content/uploads/2016/04/lrec2016-gesture-study-final-version-short.pdf},
  year           = 2016
}

@InProceedings{Pustylnikov:Mehler:Gleim:2008,
  Author         = {Abramov, Olga and Mehler, Alexander and Gleim,
                   Rüdiger},
  Title          = {A Unified Database of Dependency Treebanks.
                   Integrating, Quantifying and Evaluating Dependency Data},
  BookTitle      = {Proceedings of the 6th Language Resources and
                   Evaluation Conference (LREC 2008), Marrakech (Morocco)},
  abstract       = {This paper describes a database of 11 dependency
                   treebanks which were unified by means of a
                   two-dimensional graph format. The format was evaluated
                   with respect to storage-complexity on the one hand, and
                   efficiency of data access on the other hand. An example
                   of how the treebanks can be integrated within a unique
                   interface is given by means of the DTDB interface. },
  pdf            = {http://wwwhomes.uni-bielefeld.de/opustylnikov/pustylnikov/pdfs/LREC08_full.pdf},
  year           = 2008
}

@article{Gleim:Eger:Mehler:2019,
  author    = {Gleim, R\"{u}diger and Eger, Steffen and Mehler, Alexander and Uslu, Tolga and Hemati, Wahed and L\"{u}cking, Andy and Henlein, Alexander and Kahlsdorf, Sven and Hoenen, Armin},
  title     = {A practitioner's view: a survey and comparison of lemmatization and morphological tagging in German and Latin},
  journal   = {Journal of Language Modeling},
  year      = {2019},
  pdf = {https://www.texttechnologylab.org/wp-content/uploads/2019/07/jlm-tagging.pdf},
  doi = {10.15398/jlm.v7i1.205},
  url = {http://jlm.ipipan.waw.pl/index.php/JLM/article/view/205} 
}