@inproceedings{munoz-ortiz-etal-2021-linearizations,
    title = "Not All Linearizations Are Equally Data-Hungry in Sequence Labeling Parsing",
    author = "Mu{\~n}oz-Ortiz, Alberto  and
      Strzyz, Michalina  and
      Vilares, David",
    editor = "Mitkov, Ruslan  and
      Angelova, Galia",
    booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)",
    month = sep,
    year = "2021",
    address = "Held Online",
    publisher = "INCOMA Ltd.",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.ranlp-1.111/",
    pages = "978--988",
    abstract = "Different linearizations have been proposed to cast dependency parsing as sequence labeling and solve the task as: (i) a head selection problem, (ii) finding a representation of the token arcs as bracket strings, or (iii) associating partial transition sequences of a transition-based parser to words. Yet, there is little understanding about how these linearizations behave in low-resource setups. Here, we first study their data efficiency, simulating data-restricted setups from a diverse set of rich-resource treebanks. Second, we test whether such differences manifest in truly low-resource setups. The results show that head selection encodings are more data-efficient and perform better in an ideal (gold) framework, but that such advantage greatly vanishes in favour of bracketing formats when the running setup resembles a real-world low-resource configuration."
}