@inproceedings{kemos-etal-2019-neural,
    title = "Neural Semi-{M}arkov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging",
    author = {Kemos, Apostolos  and
      Adel, Heike  and
      Sch{\"u}tze, Hinrich},
    editor = "Burstein, Jill  and
      Doran, Christy  and
      Solorio, Thamar",
    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/N19-1280/",
    doi = "10.18653/v1/N19-1280",
    pages = "2736--2743",
    abstract = "Character-level models of tokens have been shown to be effective at dealing with within-token noise and out-of-vocabulary words. However, they often still rely on correct token boundaries. In this paper, we propose to eliminate the need for tokenizers with an end-to-end character-level semi-Markov conditional random field. It uses neural networks for its character and segment representations. We demonstrate its effectiveness in multilingual settings and when token boundaries are noisy: It matches state-of-the-art part-of-speech taggers for various languages and significantly outperforms them on a noisy English version of a benchmark dataset. Our code and the noisy dataset are publicly available at \url{http://cistern.cis.lmu.de/semiCRF}."
}