Standard
Køpsala : Transition-Based Graph Parsing via Efficient Training and Effective Encoding. / Hershcovich, Daniel; De Lhoneux, Miryam; Kulmizev, Artur; Pejhan, Elham; Nivre, Joakim.
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. Association for Computational Linguistics, 2020. p. 236-244.
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
Hershcovich, D, De Lhoneux, M, Kulmizev, A, Pejhan, E & Nivre, J 2020,
Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding. in
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. Association for Computational Linguistics, pp. 236-244, 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task, Virtual Meeting,
09/07/2020.
https://doi.org/10.18653/v1/2020.iwpt-1.25
APA
Hershcovich, D., De Lhoneux, M., Kulmizev, A., Pejhan, E., & Nivre, J. (2020).
Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding. In
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies (pp. 236-244). Association for Computational Linguistics.
https://doi.org/10.18653/v1/2020.iwpt-1.25
Vancouver
Hershcovich D, De Lhoneux M, Kulmizev A, Pejhan E, Nivre J.
Køpsala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding. In Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. Association for Computational Linguistics. 2020. p. 236-244
https://doi.org/10.18653/v1/2020.iwpt-1.25
Author
Hershcovich, Daniel ; De Lhoneux, Miryam ; Kulmizev, Artur ; Pejhan, Elham ; Nivre, Joakim. / Køpsala : Transition-Based Graph Parsing via Efficient Training and Effective Encoding. Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. Association for Computational Linguistics, 2020. pp. 236-244
Bibtex
@inproceedings{70f5b19b023445968ad3b2325c9e34b2,
title = "K{\o}psala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding",
abstract = "We present K{\o}psala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020. Our system is a pipeline consisting of off-the-shelf models for everything but enhanced graph parsing, and for the latter, a transition-based graph parser adapted from Che et al. (2019). We train a single enhanced parser model per language, using gold sentence splitting and tokenization for training, and rely only on tokenized surface forms and multilingual BERT for encoding. While a bug introduced just before submission resulted in a severe drop in precision, its post-submission fix would bring us to 4th place in the official ranking, according to average ELAS. Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.",
author = "Daniel Hershcovich and {De Lhoneux}, Miryam and Artur Kulmizev and Elham Pejhan and Joakim Nivre",
year = "2020",
doi = "10.18653/v1/2020.iwpt-1.25",
language = "English",
pages = "236--244",
booktitle = "Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies",
publisher = "Association for Computational Linguistics",
note = "16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task ; Conference date: 09-07-2020",
}
RIS
TY - GEN
T1 - Køpsala
T2 - 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task
AU - Hershcovich, Daniel
AU - De Lhoneux, Miryam
AU - Kulmizev, Artur
AU - Pejhan, Elham
AU - Nivre, Joakim
PY - 2020
Y1 - 2020
N2 - We present Køpsala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020. Our system is a pipeline consisting of off-the-shelf models for everything but enhanced graph parsing, and for the latter, a transition-based graph parser adapted from Che et al. (2019). We train a single enhanced parser model per language, using gold sentence splitting and tokenization for training, and rely only on tokenized surface forms and multilingual BERT for encoding. While a bug introduced just before submission resulted in a severe drop in precision, its post-submission fix would bring us to 4th place in the official ranking, according to average ELAS. Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.
AB - We present Køpsala, the Copenhagen-Uppsala system for the Enhanced Universal Dependencies Shared Task at IWPT 2020. Our system is a pipeline consisting of off-the-shelf models for everything but enhanced graph parsing, and for the latter, a transition-based graph parser adapted from Che et al. (2019). We train a single enhanced parser model per language, using gold sentence splitting and tokenization for training, and rely only on tokenized surface forms and multilingual BERT for encoding. While a bug introduced just before submission resulted in a severe drop in precision, its post-submission fix would bring us to 4th place in the official ranking, according to average ELAS. Our parser demonstrates that a unified pipeline is effective for both Meaning Representation Parsing and Enhanced Universal Dependencies.
U2 - 10.18653/v1/2020.iwpt-1.25
DO - 10.18653/v1/2020.iwpt-1.25
M3 - Article in proceedings
SP - 236
EP - 244
BT - Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
PB - Association for Computational Linguistics
Y2 - 9 July 2020
ER -
