This paper reduces discontinuous parsing to sequence labeling. It first shows that existing reductions for constituent parsing as labeling do not support discontinuities. Second, it fills this gap and proposes to encode tree discontinuities as nearly ordered permutations of the input sequence. Third, it studies whether such discontinuous representations are learnable. The experiments show that despite the architectural simplicity, under the right representation, the models are fast and accurate.
CITATION STYLE
Vilares, D., & Gómez-Rodríguez, C. (2020). Discontinuous constituent parsing as sequence labeling. In EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 2771–2785). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.emnlp-main.221
Mendeley helps you to discover research relevant for your work.