News

@inproceedings{Abrami:Mehler:2024,
  author    = {Abrami, Giuseppe and Mehler, Alexander},
  title     = {Efficient, uniform and scalable parallel NLP pre-processing with
               DUUI: Perspectives and Best Practice for the Digital Humanities},
  year      = {2024},
  month     = {08},
  editor    = {Karajgikar, Jajwalya and Janco, Andrew and Otis, Jessica},
  booktitle = {Digital Humanities Conference 2024 - Book of Abstracts (DH 2024)},
  location  = {Washington, DC, USA},
  series    = {DH},
  keywords  = {duui},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.13761079},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/12/DH2024_Poster.pdf},
  pdf       = {https://www.texttechnologylab.org/wp-content/uploads/2024/12/DH2024_Abstract.pdf},
  url       = {https://doi.org/10.5281/zenodo.13761079},
  pages     = {15--18},
  numpages  = {4}
}

@inproceedings{Luecking:et:al:2024,
  abstract  = {Purpose: Based on the examples of English and German, we investigate
               to what extent parsers trained on modern variants of these languages
               can be transferred to older language levels without loss. Methods:
               We developed a treebank called DoTT (https://github.com/texttechnologylab/DoTT)
               which covers, roughly, the time period from 1800 until today,
               in conjunction with the further development of the annotation
               tool DependencyAnnotator. DoTT consists of a collection of diachronic
               corpora enriched with dependency annotations using 3 parsers,
               6 pre-trained language models, 5 newly trained models for German,
               and two tag sets (TIGER and Universal Dependencies). To assess
               how the different parsers perform on texts from different time
               periods, we created a gold standard sample as a benchmark. Results:
               We found that the parsers/models perform quite well on modern
               texts (document-level LAS ranging from 82.89 to 88.54) and slightly
               worse on older texts, as expected (average document-level LAS
               84.60 vs. 86.14), but not significantly. For German texts, the
               (German) TIGER scheme achieved slightly better results than UD.
               Conclusion: Overall, this result speaks for the transferability
               of parsers to past language levels, at least dating back until
               around 1800. This very transferability, it is however argued,
               means that studies of language change in the field of dependency
               syntax can draw on dependency distance but miss out on some grammatical
               phenomena.},
  address   = {Torino, Italy},
  author    = {L{\"u}cking, Andy and Abrami, Giuseppe and Hammerla, Leon and Rahn, Marc
               and Baumartz, Daniel and Eger, Steffen and Mehler, Alexander},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational
               Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro
               and Sakti, Sakriani and Xue, Nianwen},
  month     = {may},
  pages     = {4641--4653},
  publisher = {ELRA and ICCL},
  title     = {Dependencies over Times and Tools ({D}o{TT})},
  url       = {https://aclanthology.org/2024.lrec-main.415},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/05/LREC_2024_Poster_DoTT.pdf},
  year      = {2024}
}

@inproceedings{Konca:et:al:2024,
  abstract  = {A useful semantic role-annotated resource for training semantic
               role models for the German language is missing. We point out some
               problems of previous resources and provide a new one due to a
               combined translation and alignment process: The gold standard
               CoNLL-2012 semantic role annotations are translated into German.
               Semantic role labels are transferred due to alignment models.
               The resulting dataset is used to train a German semantic role
               model. With F1-scores around 0.7, the major roles achieve competitive
               evaluation scores, but avoid limitations of previous approaches.
               The described procedure can be applied to other languages as well.},
  address   = {Torino, Italy},
  author    = {Konca, Maxim and L{\"u}cking, Andy and Mehler, Alexander},
  booktitle = {Proceedings of the 2024 Joint International Conference on Computational
               Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
  editor    = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro
               and Sakti, Sakriani and Xue, Nianwen},
  month     = {may},
  pages     = {7717--7727},
  publisher = {ELRA and ICCL},
  title     = {{G}erman {SRL}: Corpus Construction and Model Training},
  url       = {https://aclanthology.org/2024.lrec-main.682},
  poster    = {https://www.texttechnologylab.org/wp-content/uploads/2024/05/LREC_2024_Poster_GERMAN_SRL.pdf},
  year      = {2024}
}