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.
Keywords
Cite
@article{arxiv.2005.12094,
title = {K{\o}psala: Transition-Based Graph Parsing via Efficient Training and Effective Encoding},
author = {Daniel Hershcovich and Miryam de Lhoneux and Artur Kulmizev and Elham Pejhan and Joakim Nivre},
journal= {arXiv preprint arXiv:2005.12094},
year = {2020}
}
Comments
IWPT shared task 2020