Abstract
In the paper, we present a parsing technique that generates headed constituency trees, which combine information typically contained in constituency and dependency trees. We advocate for using such structures for syntactic representation. The parsing method combines prediction of dependency links with prediction of constituency spines in a ‘parsing as tagging’ approach and outputs a hybrid structure. An interesting feature is that the method can generate constituency trees with discontinuities. The parser is built on top of a BERT model for the given language and uses a specially crafted classifier for predicting dependency links. With suitable training data the method can be applied to arbitrary language; we report evaluation results for Polish and German.- Anthology ID:
- 2024.lrec-main.1106
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 12633–12643
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.1106
- DOI:
- Cite (ACL):
- Katarzyna Krasnowska-Kieraś and Marcin Woliński. 2024. Parsing Headed Constituencies. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 12633–12643, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Parsing Headed Constituencies (Krasnowska-Kieraś & Woliński, LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.1106.pdf