@inproceedings{laali-kosseim-2017-improving,
    title = "Improving Discourse Relation Projection to Build Discourse Annotated Corpora",
    author = "Laali, Majid  and
      Kosseim, Leila",
    editor = "Mitkov, Ruslan  and
      Angelova, Galia",
    booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
    month = sep,
    year = "2017",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd.",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/R17-1054/",
    doi = "10.26615/978-954-452-049-6_054",
    pages = "407--416",
    abstract = "The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit relations are often changed to explicit ones and vice-versa in the translation. In this paper, we propose a novel approach based on the intersection between statistical word-alignment models to identify unsupported discourse annotations. This approach identified 65{\%} of the unsupported annotations in the English-French parallel sentences from Europarl. By filtering out these unsupported annotations, we induced the first PDTB-style discourse annotated corpus for French from Europarl. We then used this corpus to train a classifier to identify the discourse-usage of French discourse connectives and show a 15{\%} improvement of F1-score compared to the classifier trained on the non-filtered annotations."
}