TUPA at MRP 2019: A Multi-Task Baseline System

Daniel Hershcovich, Ofir Arviv


Abstract
This paper describes the TUPA system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Because it was prepared by one of the task co-organizers, TUPA provides a baseline point of comparison and is not considered in the official ranking of participating systems. While originally developed for UCCA only, TUPA has been generalized to support all MRP frameworks included in the task, and trained using multi-task learning to parse them all with a shared model. It is a transition-based parser with a BiLSTM encoder, augmented with BERT contextualized embeddings.
Anthology ID:
K19-2002
Volume:
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
Month:
November
Year:
2019
Address:
Hong Kong
Editors:
Stephan Oepen, Omri Abend, Jan Hajic, Daniel Hershcovich, Marco Kuhlmann, Tim O’Gorman, Nianwen Xue
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
28–39
Language:
URL:
https://aclanthology.org/K19-2002
DOI:
10.18653/v1/K19-2002
Bibkey:
Cite (ACL):
Daniel Hershcovich and Ofir Arviv. 2019. TUPA at MRP 2019: A Multi-Task Baseline System. In Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning, pages 28–39, Hong Kong. Association for Computational Linguistics.
Cite (Informal):
TUPA at MRP 2019: A Multi-Task Baseline System (Hershcovich & Arviv, CoNLL 2019)
Copy Citation:
PDF:
https://aclanthology.org/K19-2002.pdf
Attachment:
 K19-2002.Attachment.zip
Data
CoNLL