Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging

Introduction

The code and dataset provided on this page was used to do the experiments presented in [1] (preprint).

The neural network is implemented in PyTorch [2].

Resources

Code: github

Dataset: will be provided soon

Cite

If you use any of the provided resources in your work, please cite the following paper:

@inproceedings{kemos2019,
  author = {Apostolos Kemos and Heike Adel and Hinrich Sch\"{u}tze},
  title = {Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging},
  booktitle = {Annual Conference of the North American Chapter of the Association for Computational Linguistics},
  month     = {June},
  year      = {2019},
  address   = {Minneapolis, USA},
  publisher = {Association for Computational Linguistics}
}

References

[1] Apostolos Kemos, Heike Adel and Hinrich Schütze: "Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging", NAACL 2019. preprint

[2] Paszke et al.: "Automatic differentiation in PyTorch", NIPS Workshop 2017.

Contact: Heike Adel (website)