Abstract
Discontinuous constituent parsers have always lagged behind continuous approaches in terms of accuracy and speed, as the presence of constituents with discontinuous yield introduces extra complexity to the task. However, a discontinuous tree can be converted into a continuous variant by reordering tokens. Based on that, we propose to reduce discontinuous parsing to a continuous problem, which can then be directly solved by any off-the-shelf continuous parser. To that end, we develop a Pointer Network capable of accurately generating the continuous token arrangement for a given input sentence and define a bijective function to recover the original order. Experiments on the main benchmarks with two continuous parsers prove that our approach is on par in accuracy with purely discontinuous state-of-the-art algorithms, but considerably faster.- Anthology ID:
- 2021.emnlp-main.825
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 10570–10578
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.825
- DOI:
- 10.18653/v1/2021.emnlp-main.825
- Cite (ACL):
- Daniel Fernández-González and Carlos Gómez-Rodríguez. 2021. Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10570–10578, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Reducing Discontinuous to Continuous Parsing with Pointer Network Reordering (Fernández-González & Gómez-Rodríguez, EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.emnlp-main.825.pdf
- Code
- danifg/Pointer-Network-Reordering
- Data
- Penn Treebank