Discontinuous Constituent Parsing as Sequence Labeling

David Vilares, Carlos Gómez-Rodríguez


Abstract
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.
Anthology ID:
2020.emnlp-main.221
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2771–2785
Language:
URL:
https://aclanthology.org/2020.emnlp-main.221
DOI:
10.18653/v1/2020.emnlp-main.221
Bibkey:
Cite (ACL):
David Vilares and Carlos Gómez-Rodríguez. 2020. Discontinuous Constituent Parsing as Sequence Labeling. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2771–2785, Online. Association for Computational Linguistics.
Cite (Informal):
Discontinuous Constituent Parsing as Sequence Labeling (Vilares & Gómez-Rodríguez, EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.221.pdf
Video:
 https://slideslive.com/38938720
Code
 aghie/disco2labels