Tüpa at SemEval-2019 Task1: (Almost) feature-free Semantic Parsing

Tobias Pütz, Kevin Glocker


Abstract
Our submission for Task 1 ‘Cross-lingual Semantic Parsing with UCCA’ at SemEval-2018 is a feed-forward neural network that builds upon an existing state-of-the-art transition-based directed acyclic graph parser. We replace most of its features by deep contextualized word embeddings and introduce an approximation to represent non-terminal nodes in the graph as an aggregation of their terminal children. We further demonstrate how augmenting data using the baseline systems provides a consistent advantage in all open submission tracks. We submitted results to all open tracks (English, in- and out-of-domain, German in-domain and French in-domain, low-resource). Our system achieves competitive performance in all settings besides the French, where we did not augment the data. Post-evaluation experiments showed that data augmentation is especially crucial in this setting.
Anthology ID:
S19-2016
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Editors:
Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
113–118
Language:
URL:
https://aclanthology.org/S19-2016
DOI:
10.18653/v1/S19-2016
Bibkey:
Cite (ACL):
Tobias Pütz and Kevin Glocker. 2019. Tüpa at SemEval-2019 Task1: (Almost) feature-free Semantic Parsing. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 113–118, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
Tüpa at SemEval-2019 Task1: (Almost) feature-free Semantic Parsing (Pütz & Glocker, SemEval 2019)
Copy Citation:
PDF:
https://aclanthology.org/S19-2016.pdf
Supplementary:
 S19-2016.Supplementary.pdf