HUJI-KU at MRP 2020: Two Transition-based Neural Parsers

Ofir Arviv, Ruixiang Cui, Daniel Hershcovich


Abstract
This paper describes the HUJI-KU system submission to the shared task on CrossFramework Meaning Representation Parsing (MRP) at the 2020 Conference for Computational Language Learning (CoNLL), employing TUPA and the HIT-SCIR parser, which were, respectively, the baseline system and winning system in the 2019 MRP shared task. Both are transition-based parsers using BERT contextualized embeddings. We generalized TUPA to support the newly-added MRP frameworks and languages, and experimented with multitask learning with the HIT-SCIR parser. We reached 4th place in both the crossframework and cross-lingual tracks.
Anthology ID:
2020.conll-shared.7
Volume:
Proceedings of the CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing
Month:
November
Year:
2020
Address:
Online
Editors:
Stephan Oepen, Omri Abend, Lasha Abzianidze, Johan Bos, Jan Hajič, Daniel Hershcovich, Bin Li, Tim O'Gorman, Nianwen Xue, Daniel Zeman
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
73–82
Language:
URL:
https://aclanthology.org/2020.conll-shared.7
DOI:
10.18653/v1/2020.conll-shared.7
Bibkey:
Cite (ACL):
Ofir Arviv, Ruixiang Cui, and Daniel Hershcovich. 2020. HUJI-KU at MRP 2020: Two Transition-based Neural Parsers. In Proceedings of the CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing, pages 73–82, Online. Association for Computational Linguistics.
Cite (Informal):
HUJI-KU at MRP 2020: Two Transition-based Neural Parsers (Arviv et al., CoNLL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.conll-shared.7.pdf