@inproceedings{marzinotto-etal-2019-maskparse,
    title = "{M}ask{P}arse@Deskin at {S}em{E}val-2019 Task 1: Cross-lingual {UCCA} Semantic Parsing using Recursive Masked Sequence Tagging",
    author = "Marzinotto, Gabriel  and
      Heinecke, Johannes  and
      Damnati, G{\'e}raldine",
    editor = "May, Jonathan  and
      Shutova, Ekaterina  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Apidianaki, Marianna  and
      Mohammad, Saif M.",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/S19-2015/",
    doi = "10.18653/v1/S19-2015",
    pages = "107--112",
    abstract = "This paper describes our recursive system for SemEval-2019 Task 1: Cross-lingual Semantic Parsing with UCCA. Each recursive step consists of two parts. We first perform semantic parsing using a sequence tagger to estimate the probabilities of the UCCA categories in the sentence. Then, we apply a decoding policy which interprets these probabilities and builds the graph nodes. Parsing is done recursively, we perform a first inference on the sentence to extract the main scenes and links and then we recursively apply our model on the sentence using a masking features that reflects the decisions made in previous steps. Process continues until the terminal nodes are reached. We chose a standard neural tagger and we focus on our recursive parsing strategy and on the cross lingual transfer problem to develop a robust model for the French language, using only few training samples"
}