@inproceedings{bourgonje-schafer-2019-multi,
    title = "Multi-lingual and Cross-genre Discourse Unit Segmentation",
    author = {Bourgonje, Peter  and
      Sch{\"a}fer, Robin},
    editor = "Zeldes, Amir  and
      Das, Debopam  and
      Galani, Erick Maziero  and
      Antonio, Juliano Desiderato  and
      Iruskieta, Mikel",
    booktitle = "Proceedings of the Workshop on Discourse Relation Parsing and Treebanking 2019",
    month = jun,
    year = "2019",
    address = "Minneapolis, MN",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W19-2714/",
    doi = "10.18653/v1/W19-2714",
    pages = "105--114",
    abstract = "We describe a series of experiments applied to data sets from different languages and genres annotated for coherence relations according to different theoretical frameworks. Specifically, we investigate the feasibility of a unified (theory-neutral) approach toward discourse segmentation; a process which divides a text into minimal discourse units that are involved in s coherence relation. We apply a RandomForest and an LSTM based approach for all data sets, and we improve over a simple baseline assuming simple sentence or clause-like segmentation. Performance however varies a lot depending on language, and more importantly genre, with f-scores ranging from 73.00 to 94.47."
}