Tackling Contradiction Detection in German Using Machine Translation and End-to-End Recurrent Neural Networks

Natural Language Inference, and specifically Contradiction Detection, is still an unexplored topic with respect to German text. In this paper, we apply Recurrent Neural Network (RNN) methods to learn contradiction-specific sentence embeddings. Our data set for evaluation is a machine-translated version of the Stanford Natural Language Inference (SNLI) corpus. The results are compared to a baseline using unsupervised vectorization techniques, namely tf-idf and Flair, as well as state-of-the art transformer-based (MBERT) methods. We find that the end-to-end models outperform the models trained on unsupervised embeddings, which makes them the better choice in an empirical use case. The RNN methods also perform superior to MBERT on the translated data set.

  • Published in:
    2020 25th International Conference on Pattern Recognition (ICPR) International Conference on Pattern Recognition (ICPR)
  • Type:
    Inproceedings
  • Authors:
    M. Pielka, R. Sifa, L. Hillebrand, D. Biesner, R. Ramamurthy, A. Ladi, C. Bauckhage
  • Year:
    2021

Citation information

M. Pielka, R. Sifa, L. Hillebrand, D. Biesner, R. Ramamurthy, A. Ladi, C. Bauckhage: Tackling Contradiction Detection in German Using Machine Translation and End-to-End Recurrent Neural Networks, International Conference on Pattern Recognition (ICPR), 2020 25th International Conference on Pattern Recognition (ICPR), 2021, https://doi.org/10.1109/ICPR48806.2021.9413257, Pielka.etal.2021,

Open BibTeX citation